© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9748
    Prev
    Next
    INDEX
    Explanations

    time of day after noon

    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_13_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
    db
    0.25
    /),
    0.24
    acetic
    0.24
    issues
    0.24
    ),
    0.23
    actic
    0.23
    ing
    0.23
    leq
    0.23
    also
    0.23
    owanego
    0.22
    POSITIVE LOGITS
     quỹ
    0.24
     кеңсе
    0.22
     esercizi
    0.22
    晝
    0.22
     introns
    0.22
     catégories
    0.22
     infinito
    0.22
     aumento
    0.21
     soir
    0.21
     doigts
    0.21
    Activations Density 0.007%

    No Known Activations