© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45122
    Prev
    Next
    INDEX
    Explanations

    Åstrand, Åhman

    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_3_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
    т
    0.66
    nahme
    0.64
    ৯
    0.64
    க்
    0.64
     связь
    0.63
    н
    0.62
    ه
    0.61
    Apakah
    0.61
    لى
    0.61
    THERE
    0.61
    POSITIVE LOGITS
    ía
    0.76
    ir
    0.66
     a
    0.64
    ím
    0.60
    ने
    0.59
    ad
    0.59
     ganas
    0.58
    ire
    0.56
     mej
    0.56
     streng
    0.55
    Activations Density 0.001%

    No Known Activations