© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159434
    Prev
    Next
    INDEX
    Explanations

    ounding or outlining

    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
    ﻧ
    1.05
    к
    1.00
    ﺭ
    1.00
    вета
    0.98
    ках
    0.96
    рав
    0.95
    خ
    0.94
    fileName
    0.92
    િક્ષ
    0.92
    για
    0.91
    POSITIVE LOGITS
    ,
    1.64
    an
    1.63
    AR
    1.46
    ↵↵
    1.35
    /
    1.32
     (
    1.30
     as
    1.30
    a
    1.28
    न
    1.28
    ad
    1.27
    Activations Density 0.000%

    No Known Activations