© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84586
    Prev
    Next
    INDEX
    Explanations

    HT abbreviations

    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_0_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
    "
    2.42
    H
    2.02
    S
    1.97
    on
    1.91
    is
    1.88
    P
    1.86
    ↵
    1.84
    F
    1.84
    t
    1.81
    '
    1.79
    POSITIVE LOGITS
    ك
    2.14
    ני
    1.49
     wilfully
    1.48
    كره
    1.48
     parametri
    1.39
    كبر
    1.38
     xhrObj
    1.35
    ING
    1.34
    كَ
    1.33
    كين
    1.31
    Activations Density 0.000%

    No Known Activations