© 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. 132882
    Prev
    Next
    INDEX
    Explanations

    Jeep

    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
    เต
    0.40
     calor
    0.40
    Tib
    0.39
    퇸
    0.38
    tom
    0.38
    roly
    0.38
     conformity
    0.37
    heated
    0.37
    akon
    0.37
     줄
    0.37
    POSITIVE LOGITS
     arrec
    0.39
     असर
    0.38
     Constru
    0.38
     سرو
    0.37
    страницу
    0.37
     WP
    0.37
    ΟΥ
    0.37
    ENANCE
    0.37
     प्राचार्य
    0.36
    чику
    0.36
    Activations Density 0.000%

    No Known Activations