© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19329
    Prev
    Next
    INDEX
    Explanations

    behavior and behavioral changes

    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_15_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
    era
    0.37
    é
    0.37
    agan
    0.36
    ase
    0.36
    romat
    0.35
    ration
    0.35
    aga
    0.35
     Casper
    0.35
     dermatitis
    0.34
    ilidad
    0.34
    POSITIVE LOGITS
     فائلوں
    0.38
     belirli
    0.37
     ہد
    0.36
     પૂ
    0.36
     dakkh
    0.36
    ኾ
    0.35
     bhikkhu
    0.34
     vecchio
    0.33
    怯
    0.33
     Queste
    0.32
    Activations Density 0.017%

    No Known Activations