© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260849
    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
     Ruby
    1.00
     ruby
    0.88
    웅
    0.85
    甚
    0.84
    su
    0.84
     Jerry
    0.82
     Mush
    0.81
    irmed
    0.80
     Het
    0.80
    queline
    0.80
    POSITIVE LOGITS
     個
    1.31
    ᖕ
    1.27
    上演
    1.26
     cohé
    1.24
     allere
    1.23
     menerapkan
    1.21
     gazing
    1.20
     exigences
    1.20
     기간
    1.19
     caractér
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.