© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60321
    Prev
    Next
    INDEX
    Explanations

    therapies

    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
    اً
    1.35
    of
    1.27
    ре
    1.25
    ру
    1.25
    اک
    1.25
    は
    1.23
    ро
    1.22
    ті
    1.20
    است
    1.20
    ते
    1.17
    POSITIVE LOGITS
    ти
    1.15
    n
    1.06
     wers
    1.05
    x
    1.04
    :”
    0.99
    ៩
    0.97
    이드
    0.95
    ,",
    0.95
    ,
    0.95
    सँग
    0.93
    Activations Density 0.000%

    No Known Activations