© 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. 199442
    Prev
    Next
    INDEX
    Explanations

    cancer, throat, passes

    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
     deposited
    0.53
    પતિ
    0.53
     bitterness
    0.53
     coltiv
    0.53
     communicative
    0.51
     kanak
    0.51
     promulgating
    0.51
     н
    0.50
     ಜಿಲ್ಲ
    0.50
     cask
    0.50
    POSITIVE LOGITS
    ا
    0.53
    ول
    0.53
    大
    0.52
    options
    0.52
    网络
    0.48
    data
    0.48
    Role
    0.48
    时间
    0.47
    y
    0.47
    ،
    0.47
    Activations Density 0.000%

    No Known Activations