© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135315
    Prev
    Next
    INDEX
    Explanations

    undoing operations

    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
    Negative Logits
    '
    1.34
     presentazione
    1.14
     presume
    1.13
     realiz
    1.11
     possono
    1.11
     pesquis
    1.09
     conduc
    1.08
     preparazione
    1.04
    ي
    1.03
     libri
    1.02
    POSITIVE LOGITS
    ab
    1.21
    S
    1.13
    ב
    1.13
    able
    1.10
    ਰ
    1.09
    T
    1.08
    د
    1.07
    ש
    1.05
    ers
    1.04
    ic
    1.03
    Activations Density 0.000%

    No Known Activations