© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9297
    Prev
    Next
    INDEX
    Explanations

    authoritarianism, participatory, tolerant tendencies

    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_13_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
    \%
    0.38
    Date
    0.37
    tab
    0.36
    br
    0.36
    ⅽ
    0.35
    Tab
    0.35
     Slides
    0.35
     \%
    0.34
    بر
    0.34
    Post
    0.34
    POSITIVE LOGITS
     dienst
    0.40
     Bulgaria
    0.38
     aph
    0.36
     выбо
    0.36
     visitation
    0.36
     Bulldog
    0.35
    личе
    0.34
     restrictive
    0.34
     autumnal
    0.33
     customer
    0.33
    Activations Density 0.078%

    No Known Activations