© 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-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260431
    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
    hes
    1.29
    д
    1.19
    ets
    1.16
    ene
    1.10
    ム
    1.05
    ös
    1.04
    Bs
    1.04
    oms
    1.01
    k
    1.01
    utations
    0.99
    POSITIVE LOGITS
    ت
    1.38
     Depreciation
    1.22
     Rhin
    1.19
    ികിത്സ
    1.18
    ScriptBuf
    1.17
     niez
    1.17
     peduncul
    1.17
    ကား
    1.14
    <unused1737>
    1.13
     Carlson
    1.13
    Activations Density 0.000%

    No Known Activations