© 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. 260476
    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
    𝒹
    1.31
     effectuer
    1.29
    𝓁
    1.28
     présent
    1.23
    𝓈
    1.22
     fleurs
    1.21
     funzioni
    1.21
     entrevista
    1.20
     camin
    1.19
    પણે
    1.19
    POSITIVE LOGITS
    ціа
    1.07
    ﻥ
    1.06
    bek
    0.99
    pv
    0.95
     cheek
    0.93
    ረጋ
    0.90
    UK
    0.90
    SEPARATOR
    0.90
    parser
    0.89
    odbc
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.