© 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. 103069
    Prev
    Next
    INDEX
    Explanations

    PHP session setup and definition

    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
    Not in Any Lists

    No Comments

    Negative Logits
     $
    1.36
     verificar
    1.19
     $\
    1.15
     recort
    1.13
    a
    1.13
     representa
    1.11
     a
    1.09
     velocità
    1.09
     recor
    1.07
     solicitar
    1.05
    POSITIVE LOGITS
    ک
    1.09
    in
    0.98
    s
    0.92
    సం
    0.91
    ad
    0.87
    andas
    0.86
    로는
    0.86
    స
    0.85
    bies
    0.83
    )」
    0.83
    Activations Density 0.001%

    No Known Activations