© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137157
    Prev
    Next
    INDEX
    Explanations

    riddle me this

    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_12_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
     indulging
    0.28
     pigments
    0.24
     iridescent
    0.24
     lễ
    0.24
     perceives
    0.24
     *
    0.23
     wardrobes
    0.23
     receptions
    0.23
     적극
    0.23
     ballots
    0.23
    POSITIVE LOGITS
    TE
    0.26
    ্টে
    0.26
    耱
    0.24
    Чер
    0.24
     hz
    0.24
    UserID
    0.23
     vp
    0.23
     srd
    0.23
    cini
    0.23
    ți
    0.23
    Activations Density 0.001%

    No Known Activations