© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227968
    Prev
    Next
    INDEX
    Explanations

    пришел, пришла, пришло, пришел

    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_6_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
    טל
    0.95
    بع
    0.82
    ర్
    0.82
    טא
    0.82
    טו
    0.82
    р
    0.81
    ט
    0.81
    지로
    0.80
    ק
    0.78
    фона
    0.77
    POSITIVE LOGITS
    un
    1.34
    um
    1.27
    ry
    1.26
    ua
    1.26
    ot
    1.25
    ri
    1.23
    ire
    1.21
    ist
    1.13
    em
    1.13
    ik
    1.13
    Activations Density 0.000%

    No Known Activations