© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 204352
    Prev
    Next
    INDEX
    Explanations

    Che

    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
    petite
    0.40
    ங்கரை
    0.39
    崠
    0.39
    ština
    0.39
    small
    0.38
     مصر
    0.38
     mali
    0.37
    Golf
    0.37
     helst
    0.37
    encias
    0.36
    POSITIVE LOGITS
     thing
    0.45
     ch
    0.45
    thing
    0.42
     च
    0.37
     Participants
    0.37
     cosa
    0.35
     отвер
    0.35
    eV
    0.35
     指輪
    0.35
     vaping
    0.35
    Activations Density 0.000%

    No Known Activations