© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2923
    Prev
    Next
    INDEX
    Explanations

    math and boolean logic problems including variables, prime number identification, and theorem mentions

    oai_token-act-pair · gemini-2.0-flash

    math number theory

    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
     kasarigan
    -1.14
     дописавши
    -1.09
    principalTable
    -1.00
    UrlResolution
    -1.00
     nakalista
    -0.97
    DispatchToProps
    -0.95
     myſelf
    -0.95
    GEBURTSDATUM
    -0.94
     صوتيه
    -0.94
    WebElementEntity
    -0.94
    POSITIVE LOGITS
    C
    0.41
     
    0.40
    k
    0.36
    <eos>
    0.35
     (
    0.34
    K
    0.34
    T
    0.33
    .
    0.33
     C
    0.32
    /
    0.31
    Activations Density 4.320%

    No Known Activations