© 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. 130453
    Prev
    Next
    INDEX
    Explanations

    reggaeton endings, Camelot, on

    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
     a
    1.29
     \
    1.07
     I
    1.06
     Æ
    1.04
     A
    1.01
     PEOPLE
    1.00
     JFK
    1.00
     którym
    0.98
     Ä
    0.98
     ADHD
    0.97
    POSITIVE LOGITS
    in
    1.61
    on
    1.42
    as
    1.34
    ين
    1.34
    지
    1.33
    ة
    1.23
    is
    1.22
    ون
    1.19
    انو
    1.16
    ю
    1.08
    Activations Density 0.000%

    No Known Activations