© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171372
    Prev
    Next
    INDEX
    Explanations

    sheer scale, number, size, complexity

    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_20_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
     शिलालेख
    0.43
     pept
    0.43
    สบาย
    0.43
     !
    0.41
     tetanus
    0.41
     ep
    0.41
     uș
    0.41
     Sankt
    0.40
     sciatic
    0.40
    jonal
    0.40
    POSITIVE LOGITS
    ビット
    0.45
     pueda
    0.43
     financières
    0.42
     વિચ
    0.41
    bit
    0.41
     attractor
    0.41
    ビ
    0.40
    濃度
    0.40
     spust
    0.40
    ვი
    0.40
    Activations Density 0.002%

    No Known Activations