© 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. 253869
    Prev
    Next
    INDEX
    Explanations

    context

    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
     vento
    0.65
    V
    0.59
     Vind
    0.56
    𝑉
    0.56
    Ｖ
    0.55
    𝒗
    0.54
     ভ
    0.52
     V
    0.50
    viat
    0.50
    𝗩
    0.50
    POSITIVE LOGITS
    W
    0.75
     W
    0.67
    Window
    0.64
    WO
    0.63
     windows
    0.62
     WINDOW
    0.61
    window
    0.61
    Ｗ
    0.60
     w
    0.59
     Window
    0.59
    Activations Density 0.004%

    No Known Activations