© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3713
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notation and terminology.

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     such
    -3.73
    such
    -3.52
    Such
    -3.36
     Such
    -3.28
     SUCH
    -2.97
     такие
    -2.09
     такой
    -2.06
     таких
    -2.06
     telles
    -2.05
     takich
    -2.03
    POSITIVE LOGITS
     الدولى
    0.71
    Tikang
    0.66
    LElement
    0.63
    __":
    0.60
     ""],
    0.59
    utrients
    0.55
    WriteBarrier
    0.55
    >",
    0.55
    artifactId
    0.55
    GenerationType
    0.55
    Activations Density 10.236%

    No Known Activations