© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179189
    Prev
    Next
    INDEX
    Explanations

    say "ian" or "ion" words

    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_50_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
    हे
    0.42
    曷
    0.41
    kbar
    0.40
    冲
    0.39
    হে
    0.39
     ヘ
    0.38
    貸款
    0.38
    ヘ
    0.38
    カラ
    0.38
    䅐
    0.38
    POSITIVE LOGITS
     pouches
    0.41
     сада
    0.41
    EU
    0.40
    ллин
    0.37
     teams
    0.37
    িসি
    0.36
    isim
    0.36
     offic
    0.36
     gac
    0.36
     fabrics
    0.36
    Activations Density 0.002%

    No Known Activations