© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90160
    Prev
    Next
    INDEX
    Explanations

    Max Planck, Maximilian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
     catalogs
    0.58
     prefers
    0.54
     rằng
    0.53
     <
    0.53
     colocar
    0.52
     tohoto
    0.52
    竖
    0.52
     enjoys
    0.51
     construire
    0.51
     formats
    0.51
    POSITIVE LOGITS
    кти
    0.54
    ﻄ
    0.54
    axis
    0.54
     Üniversitesi
    0.54
    university
    0.53
     Universität
    0.52
     মেট্রোরে
    0.51
    ہیں
    0.50
    поли
    0.50
    dued
    0.48
    Activations Density 0.000%

    No Known Activations