© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197726
    Prev
    Next
    INDEX
    Explanations

    ari

    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_4_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
    ція
    0.43
    न्ध
    0.41
    ртка
    0.41
     merci
    0.40
    親
    0.39
    рии
    0.39
     emblematic
    0.39
    кої
    0.39
    со
    0.38
    ээ
    0.38
    POSITIVE LOGITS
    ING
    0.56
    lı
    0.53
    ing
    0.52
     el
    0.50
    </i>
    0.48
    /^
    0.47
    செய்ய
    0.47
    </b>
    0.47
     Trời
    0.45
    TUR
    0.45
    Activations Density 0.001%

    No Known Activations