© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6189
    Prev
    Next
    INDEX
    Explanations

    email headers with times and dates and references to departure

    oai_token-act-pair · gemini-2.0-flash

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Kos
    -0.54
    ニング
    -0.49
     ģ
    -0.47
    fait
    -0.46
    Б
    -0.46
    king
    -0.45
    APT
    -0.45
    voir
    -0.45
    oir
    -0.45
    log
    -0.44
    POSITIVE LOGITS
     nahilalakip
    0.83
    InvalidProtocol
    0.79
    SharedCtor
    0.77
    SharedDtor
    0.77
    GTCX
    0.77
    Personendaten
    0.75
    MLLoader
    0.73
    migrationBuilder
    0.73
    WithIOException
    0.72
    Portail
    0.71
    Activations Density 1.253%

    No Known Activations