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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15523
    Prev
    Next
    INDEX
    Explanations

    sentences about people and their relationships

    oai_token-act-pair · gemini-2.0-flash

    personal stories

    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
    WebVitals
    -0.91
    tvguidetime
    -0.81
    rungsseite
    -0.76
    клопе
    -0.72
    EndContext
    -0.68
     للاسماء
    -0.66
    aarrggbb
    -0.66
     HasFactory
    -0.65
    setVerticalGroup
    -0.65
    adaptiveStyles
    -0.63
    POSITIVE LOGITS
     be
    0.51
     resist
    0.50
     meet
    0.46
    ViewImports
    0.45
     FACTORS
    0.44
    withId
    0.43
    litos
    0.43
    Bugs
    0.43
    Tiny
    0.42
     meters
    0.41
    Activations Density 3.778%

    No Known Activations