© 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. 153146
    Prev
    Next
    INDEX
    Explanations

    say "val"

    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
     WSA
    0.58
     Wexford
    0.51
    WMat
    0.49
    韦
    0.47
     WLR
    0.45
     Waterman
    0.43
     Waterford
    0.43
    unico
    0.43
     biopic
    0.43
     Witten
    0.42
    POSITIVE LOGITS
     val
    0.68
     Ч
    0.59
    Ş
    0.59
    Ш
    0.56
    val
    0.55
     Shock
    0.50
     Ш
    0.50
    Ч
    0.50
     Ş
    0.49
     Ch
    0.48
    Activations Density 0.002%

    No Known Activations