© 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. 18879
    Prev
    Next
    INDEX
    Explanations

    color palette, scheme, transformation, spaces

    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
    Ing
    0.24
     nawet
    0.22
     acoustic
    0.21
    :
    0.20
     http
    0.20
     acoustics
    0.19
    即使
    0.19
    ה
    0.19
     integrity
    0.19
    서
    0.19
    POSITIVE LOGITS
     Crook
    0.24
    数为
    0.23
     Ghaz
    0.22
    reek
    0.22
     број
    0.22
    '`--
    0.21
    女朋友
    0.21
     غز
    0.21
    átiles
    0.21
     ຊ
    0.21
    Activations Density 0.032%

    No Known Activations