© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207335
    Prev
    Next
    INDEX
    Explanations

    CSS layout 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_20_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
    杂
    0.44
    肉
    0.44
    UseDebug
    0.43
    エム
    0.43
    目の
    0.42
     flexible
    0.42
    멘
    0.41
    糈
    0.41
    𒋼
    0.41
     enhanced
    0.40
    POSITIVE LOGITS
    ubov
    0.42
    >&
    0.41
     estimado
    0.39
    वाली
    0.38
     indors
    0.38
     gloomy
    0.38
     amikor
    0.38
     clinique
    0.38
     Kirkpatrick
    0.38
     disappointing
    0.36
    Activations Density 0.000%

    No Known Activations