© 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. 108182
    Prev
    Next
    INDEX
    Explanations

    nato, ati, ato

    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
    .
    1.57
    5
    1.52
    3
    1.47
    9
    1.38
    4
    1.35
    ==
    1.28
    ado
    1.24
    ato
    1.23
    ati
    1.17
    6
    1.16
    POSITIVE LOGITS
    ী
    1.20
    ма
    1.13
    un
    1.02
    ਾ
    1.01
    ம்
    0.99
    ول
    0.98
    માં
    0.95
    い
    0.91
    ం
    0.90
    im
    0.88
    Activations Density 0.003%

    No Known Activations