© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37447
    Prev
    Next
    INDEX
    Explanations

    say "iss" or "ss"

    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_57_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
     trav
    0.40
     மற
    0.39
    stva
    0.39
    विण्यासाठी
    0.38
    雀
    0.37
     beher
    0.37
     thị
    0.36
    禍
    0.36
     clubs
    0.34
    壮
    0.34
    POSITIVE LOGITS
    Iss
    0.77
     iss
    0.66
     ss
    0.63
     Iss
    0.62
    sss
    0.62
    iss
    0.60
    íss
    0.59
    tss
    0.58
     isa
    0.57
     ISS
    0.57
    Activations Density 0.009%

    No Known Activations