© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14186
    Prev
    Next
    INDEX
    Explanations

    a variety of somewhat common words and phrases, without any clear pattern.

    oai_token-act-pair · gemini-2.0-flash

    gerunds related to tasks or actions

    np_token-act-pair-logits · gpt-4o-mini

    Actions ending in -ing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realization
    -0.82
     realisation
    -0.73
    creation
    -0.70
    ^(@)
    -0.69
    itisation
    -0.68
     preservation
    -0.68
     creation
    -0.68
     reduction
    -0.66
     acquisition
    -0.66
     imposition
    -0.66
    POSITIVE LOGITS
     distributing
    0.87
     inspecting
    0.84
     releasing
    0.83
     transferring
    0.82
     installing
    0.82
     executing
    0.81
     adjusting
    0.80
     managing
    0.80
     translating
    0.79
     reviewing
    0.78
    Activations Density 3.899%

    No Known Activations