© 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. 18017
    Prev
    Next
    INDEX
    Explanations

    forgot to

    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
    病情
    0.55
    非法
    0.54
     അപകട
    0.54
     Keaton
    0.52
    अ
    0.51
     Fitzsimmons
    0.50
     못한
    0.49
    पै
    0.49
    غذ
    0.48
     Unfall
    0.48
    POSITIVE LOGITS
     on
    0.50
     grains
    0.48
     CHAM
    0.46
     spends
    0.45
     spent
    0.45
     kyr
    0.45
     spend
    0.44
     hưởng
    0.44
    </img>
    0.43
     att
    0.43
    Activations Density 0.006%

    No Known Activations