© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46495
    Prev
    Next
    INDEX
    Explanations

    compliment

    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_13_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
     ي
    0.57
     neurons
    0.55
     أ
    0.54
    =\
    0.54
     केन्द्र
    0.51
    isions
    0.50
     ਅ
    0.50
     Nutzen
    0.50
    getCharAt
    0.50
     énergie
    0.50
    POSITIVE LOGITS
    defendant
    0.55
    cand
    0.53
    ↵
    0.51
    τυχ
    0.51
    τ
    0.49
     bra
    0.48
    cort
    0.48
    cata
    0.48
    Bra
    0.48
    dac
    0.47
    Activations Density 0.067%

    No Known Activations