© 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. 19088
    Prev
    Next
    INDEX
    Explanations

    breakfast ideas and plates

    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
    na
    0.64
     ه
    0.55
    ato
    0.53
    se
    0.52
     h
    0.51
    ab
    0.50
    nb
    0.50
    hou
    0.50
     Hou
    0.50
    =
    0.49
    POSITIVE LOGITS
     CUDA
    0.63
    </bbox>
    0.58
    ोतरी
    0.56
     moderation
    0.54
    াকিস্ত
    0.53
     pointA
    0.53
     kontrakt
    0.53
     AGR
    0.53
     переписи
    0.52
    ორცი
    0.52
    Activations Density 0.002%

    No Known Activations