© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155504
    Prev
    Next
    INDEX
    Explanations

    **

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     ae
    0.45
     wad
    0.43
     balls
    0.42
     e
    0.40
     ey
    0.40
     desco
    0.39
     pr
    0.39
     dapp
    0.38
     glistening
    0.38
     caos
    0.38
    POSITIVE LOGITS
     V
    0.61
     Pumpkin
    0.53
     Cold
    0.49
     Skull
    0.47
     Special
    0.46
     Sk
    0.46
     Slow
    0.45
     Swing
    0.45
     Top
    0.45
     Skies
    0.44
    Activations Density 0.005%

    No Known Activations