© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124732
    Prev
    Next
    INDEX
    Explanations

    Kyle Simpson Broflovski

    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
    s
    0.83
    ssä
    0.68
    to
    0.67
    sächlich
    0.64
    ädig
    0.64
    tidak
    0.63
    0
    0.61
    )”.
    0.61
    nak
    0.60
    the
    0.59
    POSITIVE LOGITS
    ו
    0.88
    ي
    0.81
    و
    0.64
    〢
    0.63
     pecans
    0.62
    ח
    0.61
     t
    0.61
     methamphetamine
    0.60
    ד
    0.58
     eran
    0.58
    Activations Density 0.000%

    No Known Activations