© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96762
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_14_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
    о
    0.69
    в
    0.69
    у
    0.61
    𝘬
    0.53
    все
    0.52
    或
    0.52
    ak
    0.50
    خ
    0.50
    الم
    0.50
    ал
    0.50
    POSITIVE LOGITS
     NHE
    0.53
    anone
    0.52
    กรรมการ
    0.52
    comodule
    0.51
    aný
    0.51
    стере
    0.50
     caballero
    0.50
    Ẻ
    0.50
    nacht
    0.49
     pajama
    0.49
    Activations Density 0.000%

    No Known Activations