© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167631
    Prev
    Next
    INDEX
    Explanations

    except

    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_31_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
     escond
    0.39
    Weak
    0.38
    Prototype
    0.38
     juror
    0.37
    رق
    0.36
    PageRoute
    0.36
    ོ
    0.36
     brilh
    0.36
    embedded
    0.36
    listBox
    0.36
    POSITIVE LOGITS
     файла
    0.49
    桷
    0.39
     centimeters
    0.38
     layout
    0.37
    usses
    0.37
     प्रदूषण
    0.36
     Sache
    0.36
     thự
    0.36
    파일명
    0.35
    秇
    0.35
    Activations Density 0.006%

    No Known Activations