© 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. 6506
    Prev
    Next
    INDEX
    Explanations

    references to figures or similar items in scientific documents or code

    oai_token-act-pair · gemini-2.0-flash

    figure references

    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
    orit
    -0.54
    wal
    -0.54
     OR
    -0.53
    cin
    -0.52
    OR
    -0.50
    atrici
    -0.50
    MR
    -0.50
     Hal
    -0.49
    fo
    -0.48
    ait
    -0.48
    POSITIVE LOGITS
     judiciaire
    0.69
    tvguidetime
    0.68
    trường
    0.66
    __':
    0.66
     tartalomajánló
    0.65
    OGND
    0.64
     feroit
    0.64
    `;
    0.64
     חיצוניים
    0.64
    脚注の使い方
    0.61
    Activations Density 2.179%

    No Known Activations