© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13885
    Prev
    Next
    INDEX
    Explanations

    Objective-C code, looking for imports, interfaces, implementations, pragmas, and other code syntax

    oai_token-act-pair · gemini-2.0-flash

    @ or #

    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
    SourceChecksum
    -0.73
    bootstrapcdn
    -0.69
    ölkerung
    -0.59
    windowFixed
    -0.56
    出版年
    -0.52
    AnimationsModule
    -0.51
     judiciaire
    -0.49
     scolaires
    -0.49
     thèse
    -0.48
     Rifle
    -0.46
    POSITIVE LOGITS
    Hentet
    0.60
    GOTREF
    0.59
    Архівовано
    0.59
    Дереккөздер
    0.53
    ITUDE
    0.51
    forRoot
    0.50
     imm
    0.49
    DialogContent
    0.49
    Приятного
    0.49
    Lycka
    0.48
    Activations Density 0.568%

    No Known Activations