© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46727
    Prev
    Next
    INDEX
    Explanations

    reinforce harmful or key messages

    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_10_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
    ă
    0.64
    ING
    0.62
    ä
    0.61
    ı
    0.60
    s
    0.57
    ing
    0.55
    ü
    0.55
    İ
    0.53
    r
    0.52
    í
    0.49
    POSITIVE LOGITS
    ుల
    0.51
    рто
    0.50
     Strengthen
    0.49
    ку
    0.48
    нди
    0.47
    occur
    0.46
    enhance
    0.46
    таж
    0.46
    obtain
    0.45
    padă
    0.45
    Activations Density 0.019%

    No Known Activations