© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260720
    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
    ie
    1.24
    و
    1.13
    hle
    1.13
    क
    1.11
    cite
    1.09
    ৬
    1.07
    ाम
    1.07
    on
    1.06
    C
    1.05
    థ
    1.04
    POSITIVE LOGITS
     desea
    1.34
     inmediata
    1.24
    prend
    1.23
     bebê
    1.19
     batches
    1.18
    ferencia
    1.16
     milliliters
    1.16
     baryon
    1.16
    幔
    1.15
     mensuales
    1.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.