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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261137
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    歿
    1.35
    ynomial
    1.32
    stargo
    1.30
    attham
    1.24
    ្ខ
    1.22
     ngram
    1.22
    луйста
    1.22
    نامه
    1.20
    WITH
    1.17
    昃
    1.16
    POSITIVE LOGITS
    ು
    1.20
    и
    1.18
    bau
    1.10
    що
    1.01
     setzte
    0.99
     poderosa
    0.96
    ger
    0.96
    ช
    0.95
    itação
    0.94
    BR
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.