© 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. 252598
    Prev
    Next
    INDEX
    Explanations

    say "ending in 'where'"

    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
     places
    1.75
     места
    1.52
     lugares
    1.49
    Places
    1.48
    places
    1.44
     Places
    1.42
     міс
    1.35
     곳
    1.32
     miejsca
    1.32
    PLACES
    1.31
    POSITIVE LOGITS
    ړه
    0.39
    ieg
    0.36
    شوند
    0.36
    डाय
    0.36
    Were
    0.35
    Ն
    0.34
    构
    0.34
    柊
    0.33
     हाय
    0.33
    matik
    0.33
    Activations Density 0.002%

    No Known Activations