© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22432
    Prev
    Next
    INDEX
    Explanations

    specific entities and terms

    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_56_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
    ঵
    0.42
     اﻻ
    0.38
    ጕ
    0.36
    װ
    0.34
    ্া
    0.34
    ⣶
    0.34
    硞
    0.33
    ‌پ
    0.33
     RICHARD
    0.33
    㩽
    0.32
    POSITIVE LOGITS
     purely
    0.35
    ith
    0.34
     separate
    0.34
    <start_of_image>
    0.34
     outboard
    0.33
     potentially
    0.32
    Steady
    0.32
     Steady
    0.32
     unified
    0.32
     forkl
    0.32
    Activations Density 0.302%

    No Known Activations