© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37818
    Prev
    Next
    INDEX
    Explanations

    hope or wish

    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_11_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
    then
    0.60
    provides
    0.59
    ul
    0.57
    de
    0.57
    also
    0.57
    Также
    0.56
    ን
    0.56
    prices
    0.55
    재
    0.55
    ദ്ദേ
    0.55
    POSITIVE LOGITS
     \
    0.64
     I
    0.59
    测
    0.57
     \|
    0.57
    ının
    0.56
     selv
    0.53
     VA
    0.52
    வால்
    0.51
    \\
    0.50
     vork
    0.50
    Activations Density 0.000%

    No Known Activations