© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112699
    Prev
    Next
    INDEX
    Explanations

    dddd, DDDD, ODD

    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_2_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
     a
    1.20
    3
    1.12
    可能
    1.09
    1
    1.09
    И
    1.05
    ás
    1.04
    两
    1.03
    个
    1.02
    一
    0.99
    خ
    0.99
    POSITIVE LOGITS
     marques
    1.13
     incul
    1.13
     inactivació
    1.13
     hurriedly
    1.12
     atteint
    1.10
     ingeniero
    1.07
    ﻳ
    1.07
     pleases
    1.05
    c
    1.05
    ান
    1.05
    Activations Density 0.000%

    No Known Activations