© 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. 3246
    Prev
    Next
    INDEX
    Explanations

    code files

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     nonatomic
    -0.49
    balleur
    -0.47
     ivelany
    -0.45
    Искәрмәләр
    -0.44
     nena
    -0.44
    înt
    -0.44
     InputDecoration
    -0.44
    tine
    -0.43
    nonatomic
    -0.43
    Vorlage
    -0.42
    POSITIVE LOGITS
    Hentet
    0.72
    ,:);
    0.61
    ']);
    0.58
    IsContent
    0.56
    isNameExpr
    0.54
     "'");
    0.54
    IContainer
    0.53
     &_
    0.52
    StructEnd
    0.52
     pulumi
    0.51
    Activations Density 48.313%

    No Known Activations