© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104463
    Prev
    Next
    INDEX
    Explanations

    rally support

    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
    บ
    1.20
    р
    1.16
     rápido
    1.05
    ท
    1.04
    ร
    1.03
    ল
    1.02
    な
    1.02
     desenvolv
    1.00
    لای
    0.95
     $\
    0.93
    POSITIVE LOGITS
    '
    1.71
    is
    1.20
    als
    1.09
    ing
    1.08
    es
    1.07
    ’
    1.05
    en
    1.03
    కు
    1.02
    os
    1.02
    ána
    0.99
    Activations Density 0.000%

    No Known Activations