© 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. 7210
    Prev
    Next
    INDEX
    Explanations

    some kind of structured metadata, identifying language, place, or structural information

    oai_token-act-pair · gemini-2.0-flash

    Foreign word pieces

    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
     dàng
    -0.49
     oct
    -0.45
     transfieras
    -0.45
    ãi
    -0.45
     zi
    -0.43
     Blackout
    -0.43
    /';
    -0.42
    Oneof
    -0.42
     =>
    -0.42
    ToProps
    -0.42
    POSITIVE LOGITS
     umana
    0.66
    ArgsConstructor
    0.60
     "..\..\..\
    0.59
     pitié
    0.57
    saraba
    0.57
     espirituales
    0.57
     végétale
    0.56
     vastaan
    0.54
     jäsen
    0.54
     <<<<<<<<<<<<<<
    0.54
    Activations Density 0.264%

    No Known Activations