© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213439
    Prev
    Next
    INDEX
    Explanations

    sle/sli

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Idris
    0.44
    INO
    0.44
    een
    0.42
     Talon
    0.38
    襲
    0.38
     ঈশ্বর
    0.36
     వే
    0.35
     Mathieu
    0.35
    Tween
    0.35
    INA
    0.35
    POSITIVE LOGITS
     manager
    0.40
    روز
    0.39
    кового
    0.39
     modifica
    0.39
     imasmim
    0.39
    饽
    0.39
     áll
    0.38
    ált
    0.38
    ിലുള്ള
    0.38
    हरण
    0.38
    Activations Density 0.001%

    No Known Activations