© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15116
    Prev
    Next
    INDEX
    Explanations

    a mix of words, but seems to be more related to identifying numbers or small numbers with measurement.

    oai_token-act-pair · gemini-2.0-flash

    parts of a whole

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     element
    -0.97
     component
    -0.96
    component
    -0.94
     segment
    -0.88
     Element
    -0.85
     chapter
    -0.85
    segment
    -0.84
     subunit
    -0.83
    element
    -0.83
     facet
    -0.82
    POSITIVE LOGITS
    жешь
    0.49
     Ngb
    0.46
     متعلقه
    0.46
    Affirmed
    0.45
     corners
    0.45
     tắt
    0.44
    ----</
    0.44
     AspNetCore
    0.44
     vôtre
    0.43
    žd
    0.43
    Activations Density 9.216%

    No Known Activations