© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5832
    Prev
    Next
    INDEX
    Explanations

    dates spanning years

    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
    ка
    1.78
    دت
    1.47
    ی
    1.36
    ب
    1.36
    е
    1.30
     Ook
    1.26
    î
    1.21
    gün
    1.21
    an
    1.20
    ı
    1.15
    POSITIVE LOGITS
    িতি
    1.53
     opcion
    1.49
    要
    1.44
     Gazette
    1.42
     Behold
    1.41
     psig
    1.41
     disguise
    1.41
    localObject
    1.38
    eret
    1.38
    Ռ
    1.37
    Activations Density 0.006%

    No Known Activations