© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27892
    Prev
    Next
    INDEX
    Explanations

    with [word]

    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_10_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
    os
    0.19
    p
    0.19
    an
    0.17
    il
    0.17
    ان
    0.16
    someone
    0.16
    c
    0.16
     isotropy
    0.15
    ку
    0.15
    qu
    0.15
    POSITIVE LOGITS
    )*
    0.17
    该
    0.17
    ﻥ
    0.16
    是一个
    0.16
     callback
    0.15
     者
    0.15
    方法
    0.15
    非
    0.15
    談
    0.15
    的方法
    0.15
    Activations Density 0.220%

    No Known Activations