© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204998
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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_37_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
    bandSize
    0.39
    SizeF
    0.39
    BSData
    0.38
     disposing
    0.37
     ทอง
    0.36
    不出
    0.35
    嘭
    0.34
     fart
    0.34
     discursive
    0.33
    渐
    0.33
    POSITIVE LOGITS
    धारी
    0.43
    케
    0.41
    retro
    0.38
     หลาย
    0.38
     <<"
    0.37
    頁
    0.36
     banana
    0.35
    Retro
    0.35
    banana
    0.35
     *((
    0.35
    Activations Density 0.001%

    No Known Activations