© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138196
    Prev
    Next
    INDEX
    Explanations

    C++ Windows API

    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_46_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
    GetValue
    0.48
     preamp
    0.42
     จำ
    0.40
    เมนต์
    0.40
     abusers
    0.39
    prefetch
    0.39
    تمبر
    0.39
    樀
    0.38
     ઘણા
    0.38
     preseason
    0.37
    POSITIVE LOGITS
     st
    0.46
    ার্থ
    0.39
    attack
    0.38
     miz
    0.38
     Attack
    0.37
     Wrong
    0.36
     বগু
    0.36
     MIND
    0.35
     Home
    0.35
     spectre
    0.34
    Activations Density 0.000%

    No Known Activations