© 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. 12233
    Prev
    Next
    INDEX
    Explanations

    code-related terms like "http", "response", "swift", "protobuf", "message"

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    anskje
    -0.61
     Efq
    -0.58
    cửa
    -0.53
    zeptember
    -0.53
     varandra
    -0.52
    tymologie
    -0.52
    ziasztok
    -0.52
     Theſe
    -0.51
    Fordítás
    -0.50
     aveug
    -0.49
    POSITIVE LOGITS
    -
    0.50
    –
    0.41
     sek
    0.37
    ,
    0.37
    ~
    0.35
    "
    0.35
    …
    0.35
    −
    0.34
    行
    0.34
    ;
    0.34
    Activations Density 6.080%

    No Known Activations