© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78732
    Prev
    Next
    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    ષ્
    0.36
    MAD
    0.35
    <?>
    0.34
    Deleg
    0.34
     doute
    0.34
     qué
    0.33
    ozer
    0.33
    tort
    0.33
    餡
    0.33
    cret
    0.32
    POSITIVE LOGITS
    淮
    0.37
    \|\
    0.37
    大きな
    0.37
    imente
    0.36
     fame
    0.36
     জমি
    0.36
     ബാ
    0.36
     campi
    0.36
     वायू
    0.36
    äte
    0.35
    Activations Density 0.007%

    No Known Activations