© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59014
    Prev
    Next
    INDEX
    Explanations

    four and Italian/French continuations

    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_2_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
    t
    1.53
    g
    1.24
    8
    1.07
    taining
    1.05
    d
    1.02
     The
    0.98
    기
    0.93
    the
    0.90
    tors
    0.86
    kons
    0.84
    POSITIVE LOGITS
    н
    1.40
    '
    1.34
    ৫
    1.27
    ’
    1.26
    ב
    1.26
    จะ
    1.21
    ه
    1.11
    น
    1.09
    你
    1.05
    ﻟ
    1.04
    Activations Density 0.002%

    No Known Activations