© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48530
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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_31_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
    꽂
    0.38
    ısından
    0.38
    Remark
    0.37
    烪
    0.37
     multimedia
    0.37
    Multicolored
    0.36
    Yeh
    0.36
    inträ
    0.36
     மகி
    0.36
     interposed
    0.36
    POSITIVE LOGITS
     श्रेणी
    0.36
     Meeting
    0.33
     Flyer
    0.33
    ([])
    0.33
     Matlab
    0.33
     शब्द
    0.32
    ﺌ
    0.32
     nucleus
    0.32
    dicts
    0.32
    बै
    0.32
    Activations Density 0.000%

    No Known Activations