© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5736
    Prev
    Next
    INDEX
    Explanations

    `maxLength`, `type` properties

    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_39_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
    ᄅ
    0.43
    涀
    0.42
     girlfriends
    0.41
     Poche
    0.39
     পলিপ
    0.38
     Blut
    0.38
     Gardiner
    0.37
     syringes
    0.37
     Guill
    0.37
    <unused609>
    0.37
    POSITIVE LOGITS
    description
    0.45
     description
    0.41
     incubation
    0.39
    inction
    0.38
    aporan
    0.38
    Description
    0.37
    ahaan
    0.37
     aut
    0.36
     DESCRIPTION
    0.36
     Description
    0.36
    Activations Density 0.003%

    No Known Activations