© 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. 5209
    Prev
    Next
    INDEX
    Explanations

    diagrams and tables

    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
    ер
    2.11
    gestion
    1.86
    𝘰
    1.85
    submitted
    1.82
    ിയ
    1.80
    𝘦
    1.78
    ЕВ
    1.76
    ionario
    1.74
    mselves
    1.70
    ⁡
    1.68
    POSITIVE LOGITS
    ا
    2.88
    a
    2.54
    elier
    2.48
    eenth
    2.05
    ية
    1.97
     aprend
    1.97
    ್
    1.92
     deterioro
    1.91
    ierstrass
    1.90
    ᴍ
    1.89
    Activations Density 0.028%

    No Known Activations