© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34871
    Prev
    Next
    INDEX
    Explanations

    Yoshua Bengio, Josh Starmer, Yoshida

    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_3_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
    ي
    0.73
    f
    0.64
    ن
    0.60
     toda
    0.59
     not
    0.58
     segunda
    0.57
    ."
    0.56
    :"
    0.56
    n
    0.55
     നല്‍
    0.55
    POSITIVE LOGITS
    кі
    0.60
    чена
    0.48
    lysis
    0.47
    unikasi
    0.46
    خب
    0.46
    ніка
    0.45
    кого
    0.45
    ων
    0.45
    amping
    0.44
    дных
    0.44
    Activations Density 0.000%

    No Known Activations