© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208261
    Prev
    Next
    INDEX
    Explanations

    need help or advice

    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_25_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
    ột
    0.38
    Hand
    0.38
    ကျွန်
    0.38
    ጄ
    0.37
     คณิตศาสตร์
    0.37
    っきり
    0.36
     temptation
    0.35
     Cavendish
    0.35
    Bluetooth
    0.35
     corrector
    0.35
    POSITIVE LOGITS
     episodi
    0.39
    ர்களை
    0.36
    bounds
    0.36
    ི
    0.36
    sequences
    0.35
    unload
    0.35
     episodios
    0.34
     آهنگ
    0.34
    native
    0.34
     তালিকা
    0.34
    Activations Density 0.000%

    No Known Activations