© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101910
    Prev
    Next
    INDEX
    Explanations

    Slim, states, kend, ID

    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_16_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
     ಔಷಧ
    0.58
     επιχει
    0.56
     விரை
    0.52
     ചികിത്സ
    0.52
    뗀
    0.51
     baseless
    0.50
     ވަ
    0.50
     ανε
    0.48
     ગાં
    0.47
     ಅಗತ್ಯ
    0.47
    POSITIVE LOGITS
    et
    0.49
    }_\
    0.46
    en
    0.45
    Musik
    0.45
    Insider
    0.45
    Music
    0.45
    ാല
    0.44
    س
    0.44
    ↵↵↵
    0.44
    el
    0.44
    Activations Density 0.000%

    No Known Activations