© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14848
    Prev
    Next
    INDEX
    Explanations

    steering wheel

    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_15_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
     f
    0.32
    РУ
    0.32
    الس
    0.31
    ی
    0.31
     오브
    0.30
     Client
    0.30
     apoi
    0.30
     Brust
    0.29
    الق
    0.29
    ಶ್ಚ
    0.29
    POSITIVE LOGITS
     бесе
    0.32
    ён
    0.31
    ట్‌
    0.30
    ያን
    0.30
    掸
    0.30
     уто
    0.29
    这话
    0.29
     Roh
    0.28
    áj
    0.28
    ūn
    0.28
    Activations Density 0.004%

    No Known Activations