© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 188
    Prev
    Next
    INDEX
    Explanations

    legal and scientific citations

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    .
    -1.85
    ,
    -1.77
    "
    -1.48
    :
    -1.45
    (
    -1.41
    -
    -1.40
    ;
    -1.39
    )
    -1.39
    /
    -1.30
    \
    -1.24
    POSITIVE LOGITS
     Theſe
    0.69
     Efq
    0.65
    ientôt
    0.65
     Anſ
    0.64
     تانيه
    0.63
    actéristi
    0.63
    ῖν
    0.63
    NUMX
    0.63
     ſeveral
    0.62
     Beſ
    0.62
    Activations Density 25.900%

    No Known Activations