© 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. 11101
    Prev
    Next
    INDEX
    Explanations

    strings of characters used in computer systems that also happen to be recognizable English words like Photo, State, and password

    oai_token-act-pair · gemini-2.0-flash

    coding/passwords

    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
    principalColumn
    -0.75
    出版年
    -0.68
     ModelExpression
    -0.63
    TagMode
    -0.62
     surla
    -0.61
    WriteBarrier
    -0.59
     createSlice
    -0.58
    DataMember
    -0.56
    stdc
    -0.56
    addCriterion
    -0.56
    POSITIVE LOGITS
    nats
    0.47
     متعلقه
    0.46
    hésite
    0.45
    Catégorie
    0.45
     skippy
    0.45
    staan
    0.44
    acular
    0.44
    fehlungen
    0.43
    NonQuery
    0.43
     senz
    0.43
    Activations Density 4.636%

    No Known Activations