© 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. 432
    Prev
    Next
    INDEX
    Explanations

    capitalized section titles and phrases

    oai_token-act-pair · gemini-2.0-flash

    Imperative verbs

    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
     Could
    -0.60
    Could
    -0.60
    Tembelea
    -0.57
     ContentValues
    -0.55
     Few
    -0.55
     Vary
    -0.55
    HasForeignKey
    -0.54
    erdings
    -0.54
    UnknownFieldSet
    -0.53
     Most
    -0.52
    POSITIVE LOGITS
     Out
    1.06
     Up
    1.03
    Out
    0.96
     Down
    0.95
     Back
    0.92
    Down
    0.86
    Up
    0.84
     Off
    0.82
     His
    0.82
     Your
    0.81
    Activations Density 6.595%

    No Known Activations