© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145611
    Prev
    Next
    INDEX
    Explanations

    alike and whole

    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_18_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
    street
    0.13
    life
    0.12
     '**
    0.12
     treba
    0.12
    straat
    0.11
    ">${
    0.11
     креди
    0.11
    >^
    0.11
    чка
    0.11
    ’”
    0.11
    POSITIVE LOGITS
     prevent
    0.13
     but
    0.12
     popular
    0.12
     대상으로
    0.12
     famously
    0.12
     advanced
    0.12
     समुद्रा
    0.12
     جلوگیری
    0.12
     com
    0.12
     thwart
    0.12
    Activations Density 0.000%

    No Known Activations