© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 36028
    Prev
    Next
    INDEX
    Explanations

    studies by named authors or groups

    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_7_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ة
    0.32
    </h2>
    0.31
    </b>
    0.31
    <0x0D>
    0.31
    ش
    0.29
    ン
    0.27
    ﻮ
    0.27
    ী
    0.26
    мы
    0.26
    يا
    0.26
    POSITIVE LOGITS
    d
    0.43
    in
    0.42
    ด
    0.40
    et
    0.34
    ali
    0.34
    dsp
    0.33
    ㅋㅋ
    0.32
    arbre
    0.32
    ed
    0.31
     robuste
    0.31
    Activations Density 0.001%

    No Known Activations