© 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. 5231
    Prev
    Next
    INDEX
    Explanations

    CH4

    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
    bigskip
    3.07
    medskip
    2.97
    ش
    2.79
    ை
    2.63
    kec
    2.57
    ್ಯ
    2.47
     menilai
    2.45
    smallskip
    2.41
     Validators
    2.39
     eget
    2.37
    POSITIVE LOGITS
    𝚊
    3.11
    መሪያ
    3.00
     быть
    2.99
    𝚎
    2.85
    volving
    2.70
    त्रेयी
    2.60
    ⺆
    2.56
    ificent
    2.56
     ukl
    2.54
    ጀመሪያ
    2.52
    Activations Density 0.003%

    No Known Activations