© 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. 103113
    Prev
    Next
    INDEX
    Explanations

    precis, sugieren, fantástica

    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
    ন
    1.80
    า
    1.41
    ン
    1.29
    н
    1.28
    on
    1.24
    其他
    1.24
    া
    1.20
    ב
    1.17
    ת
    1.16
    νες
    1.14
    POSITIVE LOGITS
    v
    1.27
    d
    1.18
    m
    1.13
    ﻭ
    1.13
    se
    1.05
    ﺩ
    1.05
    domen
    0.98
    ‌است
    0.98
    вою
    0.98
    ją
    0.97
    Activations Density 0.003%

    No Known Activations