© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125322
    Prev
    Next
    INDEX
    Explanations

    medium-sized businesses

    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_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
    ﻣ
    0.70
     contenuto
    0.68
    ма
    0.66
    ے
    0.65
     are
    0.63
    ನ್
    0.63
    ബരിമല
    0.61
     presenceData
    0.61
    мимо
    0.61
    کر
    0.60
    POSITIVE LOGITS
     -
    0.79
    S
    0.77
    A
    0.77
    W
    0.72
     (
    0.70
    I
    0.70
    er
    0.67
    0.67
    If
    0.66
    H
    0.66
    Activations Density 0.003%

    No Known Activations