© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132143
    Prev
    Next
    INDEX
    Explanations

    "ka" repeated

    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_1_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
     is
    1.09
     tyrant
    0.99
    :
    0.98
    N
    0.94
    ’
    0.93
    نا
    0.89
    R
    0.87
     verwendet
    0.85
     consulter
    0.83
    х
    0.83
    POSITIVE LOGITS
    리
    1.23
    us
    1.21
    에
    1.10
    ЗИ
    1.07
    ຜະລິດຕະພັນ
    1.06
    ৮
    1.06
    و
    1.05
    ON
    1.04
    Υ
    1.02
    ര്‍
    1.01
    Activations Density 0.000%

    No Known Activations