© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78001
    Prev
    Next
    INDEX
    Explanations

    say "t" 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_53_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
     asserting
    0.41
    ᱮ
    0.37
    憊
    0.36
    ="{
    0.35
    ācijas
    0.35
    수한
    0.34
    ujące
    0.34
     "|
    0.34
     '|
    0.34
     sizeable
    0.33
    POSITIVE LOGITS
    cx
    0.39
    롯
    0.38
    idefinite
    0.37
    孩子
    0.37
     किचन
    0.36
    Porsche
    0.36
     उत
    0.35
     Naval
    0.35
     NE
    0.35
     হুমায়
    0.35
    Activations Density 0.004%

    No Known Activations