© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67966
    Prev
    Next
    INDEX
    Explanations

    say "i" 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_46_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
    माण
    0.35
    ാരണ
    0.35
     pushbutton
    0.35
    constraintTop
    0.35
     シート
    0.34
    ℙ
    0.33
    DUCED
    0.33
     Bryan
    0.31
    ွေး
    0.31
    ேத
    0.31
    POSITIVE LOGITS
     internal
    2.55
    内
    2.53
     внутріш
    2.50
     Internal
    2.48
    Internal
    2.47
     inner
    2.44
     внутрен
    2.44
    內
    2.39
    internal
    2.36
     nội
    2.34
    Activations Density 0.107%

    No Known Activations