© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30412
    Prev
    Next
    INDEX
    Explanations

    more

    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_7_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
    0.76
    er
    0.74
    ne
    0.72
    de
    0.72
    да
    0.72
    t
    0.71
    te
    0.71
    ку
    0.71
    к
    0.70
    ot
    0.70
    POSITIVE LOGITS
    (
    0.74
     gonad
    0.63
    רג
    0.62
    이다
    0.61
    T
    0.60
    মন্ত
    0.60
     }
    0.59
     düny
    0.59
    포츠
    0.59
    درا
    0.59
    Activations Density 0.007%

    No Known Activations