© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56833
    Prev
    Next
    INDEX
    Explanations

    Make in India initiatives

    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_11_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
    0
    0.71
    ’
    0.69
    Mar
    0.67
    Been
    0.66
    RI
    0.65
    2
    0.64
    </td>
    0.64
     n
    0.59
     Marissa
    0.58
    4
    0.57
    POSITIVE LOGITS
    δά
    0.68
    бо
    0.64
    仲間
    0.61
     adversaries
    0.61
    kusen
    0.61
    銛
    0.61
    मधील
    0.60
    ència
    0.59
    ائی
    0.59
    endregion
    0.59
    Activations Density 0.001%

    No Known Activations