© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254051
    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
    Negative Logits
     article
    0.59
    article
    0.56
    posted
    0.47
    iquée
    0.45
     [...
    0.43
     artículo
    0.43
    post
    0.42
     post
    0.42
     ...,
    0.42
    ...'
    0.42
    POSITIVE LOGITS
     –
    0.57
     —
    0.55
     couldnt
    0.53
     dont
    0.49
    Cant
    0.46
     wouldnt
    0.46
    Dont
    0.46
     Dont
    0.45
    Features
    0.45
     sept
    0.44
    Activations Density 0.001%

    No Known Activations