© 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-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105958
    Prev
    Next
    INDEX
    Explanations

    frisk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    s
    1.63
    ی
    1.46
    ים
    1.40
    ের
    1.30
    ה
    1.27
    ه
    1.17
    7
    1.16
    т
    1.13
    н
    1.09
    ς
    1.09
    POSITIVE LOGITS
    ig
    1.07
    세요
    1.02
     déprimées
    0.90
    zetten
    0.89
    ચી
    0.88
    ती
    0.87
     from
    0.84
    ｐ
    0.84
     that
    0.83
    ूल
    0.82
    Activations Density 0.000%

    No Known Activations