© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156573
    Prev
    Next
    INDEX
    Explanations

    trophology, trope, trophosome

    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
    d
    1.18
    el
    1.13
    p
    1.00
    em
    0.88
    ből
    0.85
    f
    0.84
    am
    0.81
    ד
    0.80
    amai
    0.79
    fæ
    0.79
    POSITIVE LOGITS
    は
    1.30
    는
    1.25
    ва
    1.22
    ان
    1.17
    是
    1.16
    은
    1.14
    ك
    1.09
    ات
    1.08
    های
    1.08
    ا
    1.07
    Activations Density 0.001%

    No Known Activations