© 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. 227409
    Prev
    Next
    INDEX
    Explanations

    didn't mean to

    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
    ه
    1.32
    ה
    1.32
    a
    1.16
    p
    0.98
    া
    0.88
    า
    0.87
    ת
    0.84
    ти
    0.81
    هَا
    0.79
    ков
    0.77
    POSITIVE LOGITS
    5
    1.17
    4
    1.09
    1
    1.02
    3
    1.00
    änk
    0.96
    ett
    0.95
    adı
    0.95
    \*
    0.93
    hrs
    0.92
     Mistakes
    0.92
    Activations Density 0.001%

    No Known Activations