© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6700
    Prev
    Next
    INDEX
    Explanations

    places or locations

    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_44_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
     Su
    0.62
    Su
    0.54
     su
    0.49
     सु
    0.45
     coerce
    0.41
     سو
    0.40
     సు
    0.39
    苏
    0.37
    蘇
    0.37
    su
    0.36
    POSITIVE LOGITS
    ULU
    0.39
    AY
    0.39
     AY
    0.39
    QUIN
    0.39
    Kent
    0.38
    Tor
    0.38
    Help
    0.38
    кая
    0.38
     مكون
    0.37
    DELTA
    0.37
    Activations Density 0.008%

    No Known Activations