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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8747
    Prev
    Next
    INDEX
    Explanations

    ordering of things

    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
    тся
    3.01
    ー
    2.90
    ties
    2.65
    ス
    2.60
    সের
    2.49
    ✓
    2.45
    ة
    2.45
    НЕ
    2.43
    л
    2.40
    𝐧
    2.39
    POSITIVE LOGITS
    δήποτε
    3.46
    ऩे
    3.29
    ן
    2.61
    mselves
    2.60
    ı
    2.59
    ̆
    2.57
    ్
    2.46
    ки
    2.40
    ual
    2.40
    ณ์
    2.35
    Activations Density 0.115%

    No Known Activations