© 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. 208528
    Prev
    Next
    INDEX
    Explanations

    bed

    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
     w
    0.42
    烺
    0.37
     Devi
    0.36
     Clive
    0.36
     perd
    0.35
     требо
    0.34
    뇌
    0.34
     যেত
    0.33
    ترة
    0.32
     Jol
    0.32
    POSITIVE LOGITS
     Bed
    2.31
    Bed
    2.30
     bed
    2.28
    bed
    2.17
     BED
    1.91
    BED
    1.89
    床
    1.57
     Bedford
    1.45
     बेड
    1.42
    ベッド
    1.33
    Activations Density 0.001%

    No Known Activations