© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83046
    Prev
    Next
    INDEX
    Explanations

    benign, benevolent, benner

    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_0_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
    1.44
    களில்
    1.42
    li
    1.34
    tı
    1.33
    ی
    1.29
    т
    1.28
    க
    1.25
    نی
    1.23
    प
    1.23
    s
    1.22
    POSITIVE LOGITS
    :
    1.35
    ).
    1.33
    $
    1.29
    。
    1.28
    办法
    1.18
     darum
    1.16
     erster
    1.16
     doré
    1.11
    ва
    1.10
    oi
    1.10
    Activations Density 0.001%

    No Known Activations