© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175088
    Prev
    Next
    INDEX
    Explanations

    Range and Tooltip attributes

    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_24_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
    drama
    0.47
    ne
    0.47
    ographics
    0.41
    細
    0.41
    Favourite
    0.40
    栝
    0.40
    Marriage
    0.39
    credibly
    0.39
    ungsseite
    0.38
    eing
    0.38
    POSITIVE LOGITS
     cmap
    0.50
     velocidades
    0.47
    ុល
    0.46
    aciju
    0.45
     便
    0.43
     啊
    0.43
    स्करी
    0.43
     습
    0.43
    ﺤ
    0.43
     tmp
    0.42
    Activations Density 0.000%

    No Known Activations