© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30129
    Prev
    Next
    INDEX
    Explanations

    workarounds and hacks

    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_7_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
    as
    0.48
    ق
    0.46
    ע
    0.46
    د
    0.41
    ت
    0.41
    ه
    0.41
    The
    0.40
    ب
    0.40
    is
    0.39
    ח
    0.38
    POSITIVE LOGITS
     gewählt
    0.32
     złot
    0.32
     portato
    0.30
     câștig
    0.30
    も
    0.30
     disponibilité
    0.30
    ária
    0.30
    heiten
    0.29
     sareng
    0.29
     schéma
    0.29
    Activations Density 0.007%

    No Known Activations