© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10468
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific science fiction series, including character names, items, and abilities

    oai_token-act-pair · gemini-2.0-flash

    utama

    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
    writeFileSync
    -0.54
    uto
    -0.46
     }^{-
    -0.46
     neutral
    -0.44
     cung
    -0.44
    UnknownFieldSet
    -0.44
    moid
    -0.43
    <eos>
    -0.43
    ROD
    -0.43
    ут
    -0.42
    POSITIVE LOGITS
     itſelf
    0.90
     myſelf
    0.81
    Czytaj
    0.71
     purpoſe
    0.68
     Jefus
    0.68
    IntoConstraints
    0.66
     Anſ
    0.66
     Monfieur
    0.66
    fromnode
    0.65
     insuffisamment
    0.64
    Activations Density 3.830%

    No Known Activations