© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207102
    Prev
    Next
    INDEX
    Explanations

    equation symbols and 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_20_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
     tribunal
    0.38
    splitted
    0.38
     distinta
    0.37
     maxn
    0.35
     equally
    0.35
    almost
    0.35
    ົງ
    0.35
    ¯</
    0.35
    胱
    0.35
     altura
    0.34
    POSITIVE LOGITS
     acquis
    0.37
    金
    0.35
    काब
    0.35
     Goy
    0.34
    доби
    0.34
     скоро
    0.33
     Orrell
    0.33
     бом
    0.33
     Acquisitions
    0.32
    ស៊ី
    0.32
    Activations Density 0.000%

    No Known Activations