© 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. 247890
    Prev
    Next
    INDEX
    Explanations

    void

    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
    遉
    0.41
    置
    0.39
    חו
    0.39
     willen
    0.39
    way
    0.38
    ع
    0.38
    ache
    0.38
    置いて
    0.38
     chi
    0.37
    Die
    0.37
    POSITIVE LOGITS
     void
    0.69
     Void
    0.60
    Void
    0.59
     voids
    0.56
     eg
    0.48
    void
    0.47
    >.</
    0.42
    VOID
    0.40
     :).
    0.40
    ).}
    0.40
    Activations Density 0.000%

    No Known Activations