© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15999
    Prev
    Next
    INDEX
    Explanations

    words related to thinking, studying, legality or healing

    oai_token-act-pair · gemini-2.0-flash

    Situations/issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     jambes
    -0.53
     gambe
    -0.53
     piernas
    -0.53
    ύ
    -0.50
    ycznego
    -0.49
     beroep
    -0.49
     compris
    -0.48
    cious
    -0.47
    nesty
    -0.47
    पुर
    -0.47
    POSITIVE LOGITS
    SequentialGroup
    0.71
    uxxxx
    0.69
    afficheront
    0.65
    )");
    0.63
    featureID
    0.63
    Revenir
    0.62
     pinulongan
    0.62
    +};
    0.60
    °)
    0.58
     autorytatywna
    0.58
    Activations Density 3.045%

    No Known Activations