© 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. 160978
    Prev
    Next
    INDEX
    Explanations

    sp followed by common words

    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
     be
    1.50
     as
    1.50
    ،
    1.26
    ید
    1.13
     ۸
    1.13
     been
    1.13
    จะ
    1.11
    ၊
    1.09
     a
    1.08
    、
    1.08
    POSITIVE LOGITS
    t
    1.85
    től
    1.29
    '
    1.26
    यों
    1.17
    d
    1.09
    st
    1.08
    te
    1.08
    ни
    1.08
    u
    1.08
    ال
    1.07
    Activations Density 0.001%

    No Known Activations