© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245355
    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_11_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
     consequat
    1.13
     ongel
    1.11
    Defer
    1.01
    ж
    1.00
    бра
    0.98
    是要
    0.98
    рон
    0.98
     étudié
    0.97
    𝚗
    0.96
    um
    0.95
    POSITIVE LOGITS
    礻
    1.31
     hypo
    1.28
     fractal
    1.22
     stylesheet
    1.20
     symmetric
    1.18
    َي
    1.18
     biot
    1.17
     variation
    1.17
     ensured
    1.16
     replicates
    1.15
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.