© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204673
    Prev
    Next
    INDEX
    Explanations

    right to be

    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_6_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
    ่
    0.93
    in
    0.89
    ных
    0.87
    ę
    0.86
    ام
    0.83
    ной
    0.81
    ání
    0.80
     bombshell
    0.80
    elling
    0.78
    ight
    0.76
    POSITIVE LOGITS
    on
    0.86
     are
    0.86
     acredit
    0.82
    다
    0.82
     have
    0.82
    つ
    0.81
     provide
    0.81
     revitalize
    0.78
    נו
    0.76
     hanno
    0.76
    Activations Density 0.001%

    No Known Activations