© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4216
    Prev
    Next
    INDEX
    Explanations

    code documentation

    oai_token-act-pair · gemini-2.0-flash

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    package
    -0.47
    //
    -0.40
     narod
    -0.36
    assoc
    -0.35
     aikaa
    -0.34
    As
    -0.34
    нар
    -0.33
    QR
    -0.33
    cho
    -0.33
    수
    -0.32
    POSITIVE LOGITS
    ChildScrollView
    0.74
    "])
    0.74
     disponibilités
    0.69
    "]));
    0.68
    "]),
    0.67
    expandindo
    0.67
    "],
    0.67
    лтамалар
    0.66
    OOTDTY
    0.65
     protoimpl
    0.65
    Activations Density 1.012%

    No Known Activations