© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201860
    Prev
    Next
    INDEX
    Explanations

    faces away from

    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_12_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
    4
    0.35
    จะ
    0.34
    ज
    0.34
    का
    0.32
    ilibus
    0.31
    マ
    0.31
    Fresh
    0.31
    لی
    0.30
    Jul
    0.30
    ช
    0.30
    POSITIVE LOGITS
    ներ
    0.32
    нос
    0.32
    ội
    0.31
    នៃការ
    0.31
     عاوز
    0.30
     دين
    0.30
    unati
    0.29
     عندما
    0.29
     الانت
    0.29
     নিতে
    0.29
    Activations Density 0.001%

    No Known Activations