© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3432
    Prev
    Next
    INDEX
    Explanations

    help requests concerning computer programming and coding

    oai_token-act-pair · gemini-2.0-flash

    Seeking help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ArrowToggle
    -0.52
    tuuri
    -0.48
    addContainerGap
    -0.48
     tá
    -0.48
     بيها
    -0.46
     الحره
    -0.46
     seemed
    -0.46
    __((
    -0.45
     cetera
    -0.45
     comunidade
    -0.44
    POSITIVE LOGITS
     mergeFrom
    0.71
    Personendaten
    0.70
    makeConstraints
    0.61
    حوالہ
    0.59
    Välislingid
    0.58
    Toponymie
    0.57
     Ruz
    0.56
     iprot
    0.54
    posedge
    0.54
    numerusform
    0.52
    Activations Density 4.856%

    No Known Activations