© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159874
    Prev
    Next
    INDEX
    Explanations

    rightfully earned/belongs/yours

    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
     are
    1.30
     a
    1.16
    いた
    1.00
     affirme
    0.99
     atteinte
    0.97
    வ்வேறு
    0.95
     be
    0.94
    ン
    0.93
     бъдат
    0.91
     adhesions
    0.91
    POSITIVE LOGITS
    기
    1.41
    ت
    1.27
    고
    1.22
     by
    1.15
     with
    1.12
    스를
    1.09
    мо
    1.08
    ли
    1.03
    ล
    1.02
     M
    0.98
    Activations Density 0.000%

    No Known Activations