© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58071
    Prev
    Next
    INDEX
    Explanations

    un + negative adjectives

    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_11_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
    ၉
    0.35
    zić
    0.34
    EN
    0.34
    getResponse
    0.33
    =-\
    0.32
    នៃ
    0.32
    purecounter
    0.32
    hoed
    0.32
    jsce
    0.32
    =',
    0.32
    POSITIVE LOGITS
    알
    0.37
     rethink
    0.35
    ारा
    0.35
    תי
    0.34
    ében
    0.34
    ב
    0.33
    قد
    0.33
     artery
    0.32
     DBT
    0.32
     academia
    0.32
    Activations Density 0.014%

    No Known Activations