© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46318
    Prev
    Next
    INDEX
    Explanations

    easy peasy

    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_3_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
    n
    1.23
    t
    1.04
    ul
    0.88
    y
    0.86
    ur
    0.86
    il
    0.85
    ut
    0.85
    l
    0.84
    -
    0.84
    et
    0.82
    POSITIVE LOGITS
    শান্ত
    0.62
    }];
    0.61
     유사
    0.61
    كي
    0.61
    現
    0.59
    いた
    0.58
     образу
    0.58
    िटी
    0.57
     مختلف
    0.57
     산
    0.57
    Activations Density 0.001%

    No Known Activations