© 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. 473
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "Cr" or the capitalized abbreviation "Gr" as either a prefix or a standalone word

    oai_token-act-pair · 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
    libft
    -0.83
    PhysRev
    -0.81
    IntoConstraints
    -0.77
     tartalomajánló
    -0.77
    PRNewswire
    -0.76
    RenderAtEndOf
    -0.75
    HasAnnotation
    -0.75
    CGRectMake
    -0.75
    \{\\
    -0.72
    ValueStyle
    -0.70
    POSITIVE LOGITS
    ueger
    0.46
    ine
    0.44
    zug
    0.42
    sizeCache
    0.42
    usk
    0.42
    nak
    0.42
    <bos>
    0.41
     signes
    0.39
    ato
    0.39
    Aks
    0.39
    Activations Density 1.888%

    No Known Activations