© 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-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103896
    Prev
    Next
    INDEX
    Explanations

    personalization

    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
    ের
    1.07
    น
    1.06
    et
    1.03
    นั่ง
    1.03
    น้อง
    0.94
    ა
    0.92
    LA
    0.92
    ı
    0.88
     Lond
    0.86
    an
    0.84
    POSITIVE LOGITS
    ни
    1.40
    ли
    1.35
    ي
    1.29
    ю
    1.14
    ма
    1.11
    nement
    1.11
    ό
    1.10
    ين
    1.06
    اء
    1.02
    leri
    1.02
    Activations Density 0.000%

    No Known Activations