© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132373
    Prev
    Next
    INDEX
    Explanations

    nearing the end

    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
    できる
    1.13
     pressur
    1.01
    лі
    0.98
    л
    0.98
    ί
    0.98
    しながら
    0.97
    க்
    0.96
    ш
    0.96
     distância
    0.95
     talisman
    0.94
    POSITIVE LOGITS
    ,
    1.43
    The
    1.20
    D
    1.19
    9
    1.09
    :
    1.07
    an
    1.05
    G
    1.03
    8
    1.01
    a
    0.98
    were
    0.96
    Activations Density 0.000%

    No Known Activations