© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83108
    Prev
    Next
    INDEX
    Explanations

    beta-carotene and vitamin A precursor

    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_0_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
     for
    1.70
    o
    1.54
    ST
    1.26
    it
    1.10
    ir
    1.09
    e
    1.08
    p
    1.05
    a
    1.05
    DON
    1.03
    IA
    1.01
    POSITIVE LOGITS
    ৮
    1.47
    는
    1.30
    は
    1.27
    కు
    1.26
    ない
    1.25
    ها
    1.23
    ون
    1.20
    ary
    1.13
    ğini
    1.12
    কে
    1.10
    Activations Density 0.000%

    No Known Activations