© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84899
    Prev
    Next
    INDEX
    Explanations

    previous or above

    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_23_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
     scl
    0.35
    ካት
    0.35
    ফের
    0.35
     কর্মীদের
    0.35
    laš
    0.34
     نموذ
    0.34
     obrigado
    0.33
    ^{*
    0.32
    Exit
    0.32
    ilian
    0.32
    POSITIVE LOGITS
     above
    0.38
    上述
    0.36
     whereupon
    0.35
    Mà
    0.35
     douceur
    0.35
     aforementioned
    0.35
    above
    0.35
    尓
    0.35
    上限
    0.34
    cemment
    0.34
    Activations Density 0.012%

    No Known Activations