© 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. 12885
    Prev
    Next
    INDEX
    Explanations

    first-person references, especially pronouns and related words

    oai_token-act-pair · gemini-2.0-flash

    personal inclusion

    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
     payers
    -0.46
    wußt
    -0.43
    abestanden
    -0.43
    iseite
    -0.43
     Shower
    -0.41
     Trigger
    -0.40
    Millis
    -0.40
    ån
    -0.40
     binders
    -0.40
    浦
    -0.40
    POSITIVE LOGITS
     myſelf
    0.74
     Efq
    0.73
     itſelf
    0.71
     الحره
    0.69
     oneself
    0.68
     myself
    0.66
     himſelf
    0.65
     Chriftian
    0.64
     ourselves
    0.63
    ]));
    0.63
    Activations Density 3.683%

    No Known Activations