© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24599
    Prev
    Next
    INDEX
    Explanations

    ->

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Producing
    0.47
     Identify
    0.45
     ”.
    0.44
     Œ
    0.44
     ¥
    0.43
     nai
    0.43
     }.
    0.42
     Declare
    0.41
     fir
    0.41
     +.
    0.40
    POSITIVE LOGITS
    {'
    0.53
    ['
    0.52
    )->
    0.52
    ]->
    0.50
    ']->
    0.50
    radians
    0.50
    ()->
    0.50
    rand
    0.49
    ->
    0.48
    strtolower
    0.48
    Activations Density 0.001%

    No Known Activations