© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216656
    Prev
    Next
    INDEX
    Explanations

    company names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    som
    0.41
    hiyam
    0.39
    lain
    0.38
    ۢ
    0.38
    殮
    0.37
    汉
    0.36
     Som
    0.36
     BR
    0.36
     Kip
    0.36
    Som
    0.35
    POSITIVE LOGITS
     Bork
    0.43
    सागर
    0.43
     Emily
    0.42
     Ou
    0.40
    석
    0.39
    isor
    0.39
     Emission
    0.39
     ઉત્પાદ
    0.39
    ண்க
    0.38
    itext
    0.38
    Activations Density 0.007%

    No Known Activations