© 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. 260791
    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
    tery
    1.10
    iasis
    1.07
    пр
    1.06
    ہ
    1.04
    ensis
    1.03
    ac
    1.01
    蠣
    1.00
    an
    0.99
    тет
    0.99
    ti
    0.98
    POSITIVE LOGITS
     höch
    1.28
     größte
    1.28
     найбіль
    1.25
    sparsebundle
    1.25
    裟
    1.23
     ħ
    1.19
     Klicken
    1.19
     Geißler
    1.18
     matroid
    1.18
     größten
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.