© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 106381
    Prev
    Next
    INDEX
    Explanations

    Hacker News

    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_44_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
     MOD
    0.43
    果
    0.41
    Posts
    0.41
    MOD
    0.40
     posts
    0.39
     Mod
    0.39
    Mod
    0.38
    Mat
    0.38
     Posts
    0.37
     ওয়া
    0.37
    POSITIVE LOGITS
    ifInterface
    0.40
    stargo
    0.39
    osecond
    0.39
     ಪ್ರಯ
    0.39
    executer
    0.38
    $.;
    0.38
     prepar
    0.37
     augue
    0.37
    preter
    0.37
    ylene
    0.37
    Activations Density 0.000%

    No Known Activations