© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14619
    Prev
    Next
    INDEX
    Explanations

    code or function names

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
    UserScript
    -0.59
     виправивши
    -0.54
    TypedDataSet
    -0.54
     ویکی‌آمباردا
    -0.52
    Халык
    -0.51
    parsedMessage
    -0.49
    stdafx
    -0.49
     pulumi
    -0.49
    SerializedName
    -0.49
    ัพท์
    -0.48
    POSITIVE LOGITS
     defaultstate
    0.70
    horts
    0.63
    bootstrapcdn
    0.56
    IMPORTED
    0.55
    GraphicsUnit
    0.50
     Majefty
    0.49
    ことはない
    0.48
    μφωνα
    0.47
    نسي
    0.47
    astrous
    0.47
    Activations Density 5.160%

    No Known Activations