© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258139
    Prev
    Next
    INDEX
    Explanations

    Pause Updates

    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_22_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
    ত্ত
    0.48
     Tabelle
    0.48
     شك
    0.46
    す
    0.46
    日数
    0.45
    skiej
    0.45
     кухни
    0.44
    ಿದ್ದೇನೆ
    0.44
    申し
    0.44
    ૪
    0.44
    POSITIVE LOGITS
     nature
    0.43
    փ
    0.39
     jako
    0.39
     halo
    0.39
    Nature
    0.39
     Nature
    0.38
     whiche
    0.38
     použí
    0.38
     Woodson
    0.38
    Փ
    0.38
    Activations Density 0.000%

    No Known Activations