© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 7998
    Prev
    Next
    INDEX
    Explanations

    question answering and mathematical proofs

    oai_token-act-pair · gemini-2.0-flash

    Proof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    lip
    -0.42
    etc
    -0.39
    bor
    -0.38
    sip
    -0.38
    cap
    -0.37
    apt
    -0.37
    sin
    -0.35
    ion
    -0.35
    me
    -0.35
    os
    -0.35
    POSITIVE LOGITS
    ChildScrollView
    0.60
     myſelf
    0.60
    VersionUID
    0.54
     Theſe
    0.54
    ViewImports
    0.53
    ^(@)
    0.53
     ujednoznacz
    0.53
     greateſt
    0.52
     becauſe
    0.52
     ſeveral
    0.52
    Activations Density 0.758%

    No Known Activations