© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60870
    Prev
    Next
    INDEX
    Explanations

    speechless or wow followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    𝑘
    0.46
    ро
    0.40
     collim
    0.40
    ك
    0.39
    니다
    0.39
     for
    0.38
    та
    0.37
    ций
    0.37
     permitt
    0.36
    هم
    0.36
    POSITIVE LOGITS
    upu
    0.40
    S
    0.38
    ándose
    0.38
    Ile
    0.37
     Autres
    0.36
     Benefits
    0.35
    aruhi
    0.35
    vani
    0.35
    bearing
    0.35
    ньше
    0.35
    Activations Density 0.010%

    No Known Activations