© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17978
    Prev
    Next
    INDEX
    Explanations

    amounts or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     많은
    0.37
     ㅏ
    0.36
    不少
    0.35
    ⓘ
    0.34
    kül
    0.34
     veditabbo
    0.34
    ρης
    0.33
    搽
    0.33
    知らせ
    0.33
     mar
    0.33
    POSITIVE LOGITS
    months
    0.56
     months
    0.54
     weeks
    0.53
     maanden
    0.51
    weeks
    0.47
    dozen
    0.47
    minutes
    0.45
    Months
    0.44
     Months
    0.44
     years
    0.43
    Activations Density 0.172%

    No Known Activations