© 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. 133335
    Prev
    Next
    INDEX
    Explanations

    aliens, aliased, Al

    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
    ri
    1.20
     =
    1.12
    \%
    1.03
     doesn
    0.98
    d
    0.92
    ra
    0.89
     spreads
    0.89
     fates
    0.89
     reputations
    0.88
    ၀၀
    0.88
    POSITIVE LOGITS
    ش
    1.51
    ان
    1.41
    ту
    1.27
    an
    1.26
    ну
    1.13
    ب
    1.13
    ты
    1.11
    는
    1.11
    ш
    1.10
    ก
    1.10
    Activations Density 0.000%

    No Known Activations