© 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. 39492
    Prev
    Next
    INDEX
    Explanations

    words ending with suffixes like -ency, -liness, -ly, or -cut

    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
    t
    0.89
    ان
    0.82
    ל
    0.82
    l
    0.81
    ล
    0.74
    girl
    0.71
    ри
    0.71
    j
    0.69
    lc
    0.69
    .
    0.69
    POSITIVE LOGITS
    )。
    0.71
    íb
    0.71
    ）。
    0.64
     nervously
    0.60
    ços
    0.58
    áva
    0.57
    ்க
    0.56
     conclusively
    0.55
     definición
    0.55
    ScriptBuf
    0.55
    Activations Density 0.025%

    No Known Activations