© 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. 204141
    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_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
     dark
    0.45
    DARK
    0.44
    Dark
    0.42
    暗
    0.42
     暗
    0.40
     DARK
    0.40
     Dark
    0.39
     upotre
    0.39
    dark
    0.39
    ダーク
    0.38
    POSITIVE LOGITS
     bed
    0.56
     Bed
    0.55
    床
    0.54
     床
    0.52
    床上
    0.52
     rooms
    0.51
     Staff
    0.51
    Bed
    0.50
     Rooms
    0.50
     Beds
    0.50
    Activations Density 0.000%

    No Known Activations