© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90447
    Prev
    Next
    INDEX
    Explanations

    piece of work

    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_3_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
    的
    0.86
    ة
    0.84
    이지만
    0.81
     in
    0.81
    ও
    0.80
    6
    0.80
    5
    0.79
    น
    0.79
    ุ
    0.77
    의
    0.73
    POSITIVE LOGITS
    ng
    0.69
    ﻁ
    0.69
    ަން
    0.66
    ngram
    0.66
    g
    0.64
    c
    0.64
    ról
    0.63
    xam
    0.62
    ﻥ
    0.61
    xido
    0.60
    Activations Density 0.001%

    No Known Activations