© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136532
    Prev
    Next
    INDEX
    Explanations

    Roman numeral analysis

    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_12_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
    িলিয়া
    0.70
     ساين
    0.66
     காட்சி
    0.65
     dizajn
    0.65
    x
    0.64
     azul
    0.63
     నుండి
    0.63
    瓈
    0.61
     Citi
    0.60
     biru
    0.60
    POSITIVE LOGITS
    0.57
    至於
    0.54
    urgeon
    0.52
    posing
    0.52
    quele
    0.52
    äv
    0.50
    <0xAF>
    0.50
     summarised
    0.50
    /
    0.49
    ছে
    0.48
    Activations Density 0.000%

    No Known Activations