© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156632
    Prev
    Next
    INDEX
    Explanations

    la + common noun

    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_2_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
    س
    1.29
    ק
    1.24
    ных
    1.22
    к
    1.18
    ،
    1.18
    ى
    1.17
    ों
    1.13
     I
    1.11
    ке
    1.11
    я
    1.11
    POSITIVE LOGITS
    an
    1.66
    ان
    1.20
    AG
    1.03
     jedem
    0.92
     hva
    0.91
     apie
    0.90
    on
    0.89
    and
    0.89
     cittadini
    0.89
    มีความ
    0.86
    Activations Density 0.001%

    No Known Activations