© 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. 8844
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to biology and chemistry

    oai_token-act-pair · gemini-2.0-flash

    surface

    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
     Roskov
    -0.91
    évaluateur
    -0.87
    Билгалдахарш
    -0.84
     propOrder
    -0.84
     eventdata
    -0.81
    tisseur
    -0.75
    Personensuche
    -0.75
    InSection
    -0.75
    FunctionFlags
    -0.74
    WebElementEntity
    -0.73
    POSITIVE LOGITS
     surface
    0.85
     wall
    0.84
     floor
    0.76
     membrane
    0.72
     ceiling
    0.69
    surface
    0.68
     edge
    0.67
     beach
    0.66
     border
    0.66
     stage
    0.63
    Activations Density 8.827%

    No Known Activations