© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83723
    Prev
    Next
    INDEX
    Explanations

    flavour

    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_0_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
    l
    1.67
    n
    1.51
    se
    1.50
    p
    1.50
    larni
    1.48
     that
    1.39
    면
    1.38
    ま
    1.37
    न
    1.36
    ز
    1.35
    POSITIVE LOGITS
     حكم
    1.42
     عين
    1.24
     صحيح
    1.23
     قيم
    1.20
     دين
    1.19
     ريا
    1.18
    ка
    1.14
     může
    1.14
     تحقيق
    1.14
    事情
    1.13
    Activations Density 0.000%

    No Known Activations