© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227689
    Prev
    Next
    INDEX
    Explanations

    what's up

    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
    ل
    1.27
    ל
    1.03
    ال
    1.02
    لين
    1.01
    il
    0.94
    ए
    0.94
    াল
    0.92
    انية
    0.87
    nij
    0.87
    נ
    0.87
    POSITIVE LOGITS
     allemand
    0.93
    don
    0.77
    до
    0.77
     annuel
    0.77
     불구하고
    0.77
    dı
    0.75
     conséquent
    0.75
     factores
    0.75
     títulos
    0.74
    ца
    0.73
    Activations Density 0.000%

    No Known Activations