© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5106
    Prev
    Next
    INDEX
    Explanations

    enchufes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    い
    1.95
    er
    1.92
    tive
    1.89
     Roskov
    1.85
    qiya
    1.83
    ีน
    1.80
    𝗅
    1.79
    hai
    1.78
    ଁ
    1.76
     schimb
    1.73
    POSITIVE LOGITS
    प्लीट
    2.03
    द
    1.90
    entlich
    1.89
    न
    1.84
     рукой
    1.78
    keys
    1.76
    雇
    1.74
    ENGE
    1.67
    زمان
    1.66
     leeway
    1.66
    Activations Density 0.000%

    No Known Activations