© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41362
    Prev
    Next
    INDEX
    Explanations

    v, outcomes, together, or too

    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_22_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
     firmly
    0.47
    n
    0.47
     a
    0.45
    tu
    0.44
     create
    0.44
     Abi
    0.43
     thereby
    0.43
    a
    0.43
    esso
    0.42
     reduce
    0.41
    POSITIVE LOGITS
    𝙫
    0.46
    Disconnected
    0.45
    ImageBeforeText
    0.45
     उड़
    0.43
     movimientos
    0.43
     замет
    0.43
     fő
    0.42
     मेल
    0.42
     ब्याज
    0.41
    琬
    0.41
    Activations Density 0.000%

    No Known Activations