© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46989
    Prev
    Next
    INDEX
    Explanations

    get elements by tag name/id

    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_10_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
    0.51
    so
    0.44
    u
    0.44
    lo
    0.44
    j
    0.43
    us
    0.42
    lar
    0.42
    lari
    0.41
    d
    0.41
    la
    0.40
    POSITIVE LOGITS
    ции
    0.29
     avatar
    0.29
     finden
    0.27
    InputChange
    0.26
     avenue
    0.26
     artery
    0.26
     чаще
    0.26
    ](#
    0.26
     delle
    0.25
    /
    0.25
    Activations Density 0.029%

    No Known Activations