© 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. 160983
    Prev
    Next
    INDEX
    Explanations

    ash or asher

    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
    uje
    1.05
     في
    1.00
    in
    0.93
    ur
    0.91
     variété
    0.89
     در
    0.87
     inorder
    0.87
    ﻝ
    0.86
    ولا
    0.86
    ولة
    0.85
    POSITIVE LOGITS
     as
    1.38
     the
    1.21
     by
    1.13
    USE
    1.13
     a
    1.09
    জ
    1.02
    스
    1.02
    0
    1.01
    ות
    0.98
    ้น
    0.94
    Activations Density 0.000%

    No Known Activations