© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13747
    Prev
    Next
    INDEX
    Explanations

    code and code-like syntax with some emphasis on 'override'.

    oai_token-act-pair · gemini-2.0-flash

    Programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    τως
    -0.46
    GetMapping
    -0.46
    8
    -0.44
    mately
    -0.43
    ering
    -0.43
    getMenuInflater
    -0.42
     res
    -0.41
     fak
    -0.40
    TRIBUT
    -0.39
    пания
    -0.38
    POSITIVE LOGITS
     gynhyrchwyd
    0.85
     незавершена
    0.80
     surla
    0.73
    Gweler
    0.70
     بيها
    0.70
    enumi
    0.69
     '\\;'
    0.69
    TRIBUN
    0.66
    roek
    0.63
    UseVisualStyle
    0.62
    Activations Density 1.972%

    No Known Activations