© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34155
    Prev
    Next
    INDEX
    Explanations

    step 1:

    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_3_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
    s
    0.95
    í
    0.89
    p
    0.81
    ח
    0.80
    sel
    0.73
    á
    0.71
    ৫
    0.68
    g
    0.66
    z
    0.64
    jä
    0.64
    POSITIVE LOGITS
    。
    0.73
    اوی
    0.70
     will
    0.66
    ра
    0.65
    >$
    0.63
    ER
    0.61
     bước
    0.60
    दा
    0.59
    ה
    0.59
    Е
    0.58
    Activations Density 0.002%

    No Known Activations