© 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. 170673
    Prev
    Next
    INDEX
    Explanations

    then now

    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
     keeping
    0.42
    갱
    0.41
     top
    0.41
     až
    0.40
    b
    0.39
    ब
    0.38
    अ
    0.38
     thống
    0.38
     dễ
    0.38
     minimizing
    0.38
    POSITIVE LOGITS
    菉
    0.46
    CTURE
    0.45
    ؟
    0.45
     حضرت
    0.42
    )]:
    0.41
    ))-
    0.41
     кеңсеси
    0.40
     chứ
    0.40
    acay
    0.39
    㕩
    0.39
    Activations Density 0.007%

    No Known Activations