© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176479
    Prev
    Next
    INDEX
    Explanations

    zone, math, systems, all, index, stands

    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_24_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
    ប្ប
    0.38
    initState
    0.38
     administrativa
    0.37
     plaie
    0.35
    撥
    0.35
     administrativas
    0.35
    企業
    0.34
     Angleterre
    0.34
    érus
    0.33
    panels
    0.33
    POSITIVE LOGITS
     ich
    0.41
     Zul
    0.40
    _{-}\
    0.39
    ících
    0.38
    ాలతో
    0.38
     取
    0.37
     சக
    0.37
     TODOS
    0.37
     много
    0.36
     pickled
    0.36
    Activations Density 0.000%

    No Known Activations