© 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. 131239
    Prev
    Next
    INDEX
    Explanations

    technical systems

    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
    akkhand
    0.43
     झ
    0.40
     itemscope
    0.40
     Ezekiel
    0.39
     lowercase
    0.38
    Prec
    0.38
    ㄾ
    0.38
     पूंजी
    0.38
     uppercase
    0.37
     زنج
    0.37
    POSITIVE LOGITS
    ="__
    0.43
     mull
    0.38
    Mann
    0.37
    heira
    0.37
    ムー
    0.37
     constable
    0.37
     caballos
    0.36
     sympy
    0.36
    ချ
    0.36
     Cient
    0.35
    Activations Density 0.010%

    No Known Activations