© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112949
    Prev
    Next
    INDEX
    Explanations

    joining together

    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_2_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
    ت
    1.07
    ل
    1.00
    고
    0.89
    त
    0.88
    τή
    0.81
    تهم
    0.81
    し
    0.80
    ת
    0.80
    보
    0.80
    不会
    0.79
    POSITIVE LOGITS
    ING
    1.01
     of
    0.94
     are
    0.90
    of
    0.87
    2
    0.85
    ri
    0.81
    0.78
    were
    0.77
    that
    0.77
    ral
    0.74
    Activations Density 0.003%

    No Known Activations