© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213788
    Prev
    Next
    INDEX
    Explanations

    Label

    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_47_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
    貼
    0.42
    стика
    0.41
    stic
    0.39
    rosion
    0.37
    貼り
    0.37
    ηση
    0.36
    🅐
    0.36
    ناہ
    0.36
    ylob
    0.35
    ನಾ
    0.35
    POSITIVE LOGITS
     Kant
    0.44
    Kant
    0.41
    熒
    0.38
     Hancock
    0.38
    tze
    0.38
     Heart
    0.37
    CHT
    0.37
     Cant
    0.37
     CNT
    0.37
    cht
    0.36
    Activations Density 0.001%

    No Known Activations