© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123804
    Prev
    Next
    INDEX
    Explanations

    School Letterhead

    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
    د
    0.89
    os
    0.70
    い
    0.65
    quela
    0.63
    ד
    0.62
    ನ
    0.62
    )
    0.59
    +\
    0.58
    দ
    0.57
    =\
    0.57
    POSITIVE LOGITS
     by
    0.69
    to
    0.63
    by
    0.61
     boarded
    0.61
     as
    0.59
    hline
    0.59
     ampli
    0.57
     তৃতীয়
    0.57
     victimization
    0.57
     cooks
    0.57
    Activations Density 0.001%

    No Known Activations