© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14098
    Prev
    Next
    INDEX
    Explanations

    legal and official documents

    oai_token-act-pair · gemini-2.0-flash

    legal/research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     grant
    -2.38
    Grant
    -2.20
    grant
    -2.16
     Grant
    -2.16
     grants
    -2.14
     Grants
    -2.13
     GRANT
    -2.06
    Grants
    -2.02
    grants
    -1.94
    GRANT
    -1.87
    POSITIVE LOGITS
    DataSetChanged
    0.57
     فريبيس
    0.53
    INSEE
    0.51
    WithIOException
    0.49
    braun
    0.47
    abestanden
    0.46
     useDispatch
    0.46
    ärme
    0.46
     pulito
    0.45
     समीक्षाएं
    0.45
    Activations Density 2.263%

    No Known Activations