© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48000
    Prev
    Next
    INDEX
    Explanations

    j, 'j', J's

    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
    in
    1.55
    1
    1.00
    2
    0.96
    board
    0.89
    NP
    0.89
    lock
    0.81
    search
    0.80
    play
    0.79
    hold
    0.79
    check
    0.79
    POSITIVE LOGITS
    м
    1.26
    م
    1.23
    ت
    1.18
    ة
    1.16
    ل
    1.13
    ம்
    1.08
    ب
    1.05
    ک
    0.99
    س
    0.98
    い
    0.97
    Activations Density 0.035%

    No Known Activations