© 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. 13712
    Prev
    Next
    INDEX
    Explanations

    noch

    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
    시아
    0.55
    诺
    0.53
     colours
    0.52
    w
    0.50
    چ
    0.47
     colour
    0.46
    在她
    0.45
     place
    0.45
     commandments
    0.44
     silicon
    0.43
    POSITIVE LOGITS
    Parameter
    0.52
    
    0.52
    yt
    0.51
     বলিলাম
    0.51
     искать
    0.51
    ij
    0.50
     অনুসন্ধান
    0.50
    ieh
    0.50
    acer
    0.49
    yr
    0.49
    Activations Density 0.000%

    No Known Activations