© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6140
    Prev
    Next
    INDEX
    Explanations

    descriptions of light and its interaction with the surroundings, including verbs describing movement and location.

    oai_token-act-pair · gemini-2.0-flash

    flowing movement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     myſelf
    -1.20
     ſeveral
    -1.04
     himſelf
    -1.02
     pleaſure
    -1.02
     Shakspeare
    -1.00
    DockStyle
    -1.00
     doInBackground
    -0.99
     ſche
    -0.99
    ]--;
    -0.98
     vPvB
    -0.98
    POSITIVE LOGITS
     its
    0.54
     suo
    0.48
     strongly
    0.44
     like
    0.44
     from
    0.44
     [
    0.43
     Q
    0.43
    q
    0.42
     Its
    0.42
     sua
    0.42
    Activations Density 3.774%

    No Known Activations