© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115674
    Prev
    Next
    INDEX
    Explanations

    program `return` value

    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_27_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
    锆
    0.46
    裨
    0.41
    ავ
    0.39
     худож
    0.39
     dealer
    0.38
     dealers
    0.38
     глу
    0.38
    unpriv
    0.38
    跗
    0.37
     reproduction
    0.37
    POSITIVE LOGITS
     Platform
    0.40
     slob
    0.38
    Abb
    0.37
     Fig
    0.37
    cite
    0.36
    Platform
    0.36
     consented
    0.36
    Fig
    0.35
    “…
    0.35
     Telef
    0.35
    Activations Density 0.038%

    No Known Activations