© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50394
    Prev
    Next
    INDEX
    Explanations

    "con" followed by a word

    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_30_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
     Diseño
    0.38
    inicio
    0.37
     firef
    0.36
    😶
    0.35
     refuses
    0.35
     කොට
    0.34
     corner
    0.34
     monetize
    0.33
     Rxc
    0.33
    市の
    0.33
    POSITIVE LOGITS
    ienced
    0.35
     шо
    0.35
     fives
    0.35
    Chevrolet
    0.34
    Ал
    0.34
    衊
    0.34
     hur
    0.34
    ේ
    0.34
    Tum
    0.34
    Strawberry
    0.34
    Activations Density 0.006%

    No Known Activations