© 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. 160946
    Prev
    Next
    INDEX
    Explanations

    nuestra / nuestros

    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
    ă
    1.22
    َس
    1.19
     Người
    1.17
    2
    1.09
    该
    1.06
     of
    1.01
     Posteriormente
    1.01
    人們
    0.99
    芨
    0.99
    يد
    0.98
    POSITIVE LOGITS
    ன்
    1.02
     don
    0.95
    cession
    0.84
    هِ
    0.84
    ாண்டு
    0.82
     as
    0.81
    reaching
    0.81
    aré
    0.80
     courting
    0.78
    $).
    0.77
    Activations Density 0.006%

    No Known Activations