© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252513
    Prev
    Next
    INDEX
    Explanations

    пло

    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_56_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
     fl
    0.44
    fl
    0.38
    icult
    0.38
    teras
    0.37
     اي
    0.36
     Radial
    0.35
    лич
    0.35
    랩
    0.35
    ierz
    0.34
     прида
    0.34
    POSITIVE LOGITS
     skid
    0.63
     Skid
    0.60
     skip
    0.59
     skipping
    0.58
     ski
    0.57
     Ski
    0.57
     Ska
    0.56
    sk
    0.56
     SK
    0.56
     skiing
    0.56
    Activations Density 0.000%

    No Known Activations