© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8757
    Prev
    Next
    INDEX
    Explanations

    capitalized words, abbreviations, locations or places

    oai_token-act-pair · gemini-2.0-flash

    ia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Fernsehserie
    -0.46
     ap
    -0.44
    Vas
    -0.43
    mac
    -0.42
    屆
    -0.42
     ex
    -0.42
    ruff
    -0.41
     relative
    -0.41
    мак
    -0.41
    localctx
    -0.41
    POSITIVE LOGITS
     Theſe
    0.81
     EconPapers
    0.79
     myſelf
    0.79
     Reſ
    0.78
    ſelf
    0.77
     Efq
    0.77
     purpoſe
    0.77
    tvguidetime
    0.77
     auffi
    0.76
     ISNI
    0.74
    Activations Density 0.461%

    No Known Activations