Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14511
    Prev
    Next
    INDEX
    Explanations

    instances of people doing things in specific locations or groups uniting

    oai_token-act-pair · gemini-2.0-flash

    pitch

    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
    MigrationBuilder
    -0.62
    SequentialGroup
    -0.60
    ActionCreators
    -0.52
    jestic
    -0.51
    webElement
    -0.50
    FromJson
    -0.50
    /**
    -0.50
     jā
    -0.49
    providedIn
    -0.49
    PDF
    -0.49
    POSITIVE LOGITS
    pitch
    0.86
     pitch
    0.80
     pitches
    0.76
     pitching
    0.76
     Pitch
    0.73
    Pitch
    0.73
    RenderAtEndOf
    0.73
     pitched
    0.71
     band
    0.68
     banding
    0.64
    Activations Density 1.378%

    No Known Activations