© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210983
    Prev
    Next
    INDEX
    Explanations

    coordinates, locations, groups, text preceding specific tokens

    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_19_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
    *\*
    0.46
    被称为
    0.44
     Lé
    0.43
     控制
    0.43
     electorate
    0.43
     Lehman
    0.42
     Dispute
    0.41
     لي
    0.40
    。</
    0.40
    賴
    0.40
    POSITIVE LOGITS
    2
    0.63
    AVE
    0.56
    4
    0.54
    5
    0.53
    ponsors
    0.52
    3
    0.52
    fertil
    0.51
    0
    0.51
    на
    0.51
    Array
    0.50
    Activations Density 0.000%

    No Known Activations