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. 261569
    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
    ن
    1.47
     schematic
    1.20
    ل
    1.20
     precise
    1.17
    स
    1.14
     Barcelone
    1.14
    ression
    1.12
     planification
    1.12
     충분
    1.11
    এই
    1.11
    POSITIVE LOGITS
    "$
    1.12
     каждое
    1.12
    insured
    1.11
     bawa
    1.09
     совершенно
    1.07
     отдельно
    1.05
     Urinary
    1.01
     Adventures
    1.01
    lishes
    0.99
     karya
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.