© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203310
    Prev
    Next
    INDEX
    Explanations

    parts of the body

    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_12_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
     头
    0.33
    ोग्राफी
    0.31
     प्रीमियम
    0.31
    lebnis
    0.31
    >.</
    0.30
    sette
    0.30
     subtiliter
    0.30
    gota
    0.30
     以及
    0.30
    lifts
    0.30
    POSITIVE LOGITS
     bank
    0.37
    и
    0.33
    να
    0.32
     literary
    0.30
     trap
    0.29
     box
    0.28
     quadri
    0.28
     deer
    0.27
     ceux
    0.27
     clause
    0.27
    Activations Density 0.001%

    No Known Activations