© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203195
    Prev
    Next
    INDEX
    Explanations

    empty string or punctuation

    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_25_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
    ใส
    0.41
     containing
    0.38
    čkog
    0.38
     tavolo
    0.37
     מצ
    0.37
     perché
    0.36
    的看着
    0.36
    後
    0.36
    우
    0.36
     jatuh
    0.36
    POSITIVE LOGITS
    尼亚克
    0.38
    bür
    0.37
    හෝ
    0.37
     நிச்சயமாக
    0.37
     ALPINE
    0.36
    芴
    0.36
     ALP
    0.36
    áló
    0.35
     BOM
    0.35
    álás
    0.35
    Activations Density 0.000%

    No Known Activations