© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7488
    Prev
    Next
    INDEX
    Explanations

    changes in the performance of repeated actions, or warnings about avoiding something.

    oai_token-act-pair · gemini-2.0-flash

    keep/stop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    RefNanny
    -0.78
     مشين
    -0.69
    xodo
    -0.67
    ]--;
    -0.67
    Enllaces
    -0.65
    ^(@)
    -0.65
     certes
    -0.64
     refusé
    -0.64
     {}));
    -0.63
    AndroidJUnit
    -0.63
    POSITIVE LOGITS
     being
    1.20
     giving
    1.07
     making
    1.02
     taking
    1.02
    being
    0.97
     doing
    0.96
     getting
    0.93
     creating
    0.90
     appearing
    0.90
     having
    0.89
    Activations Density 1.018%

    No Known Activations