© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209003
    Prev
    Next
    INDEX
    Explanations

    salvage, fighting, optimization, effort

    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_20_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
    占
    0.40
     поддержа
    0.39
     inlets
    0.38
     ново
    0.37
    строи
    0.37
     பல
    0.37
     contaminated
    0.37
    ₁,
    0.36
     posterity
    0.36
     canal
    0.36
    POSITIVE LOGITS
    Sour
    0.46
    Minutes
    0.45
    Hours
    0.44
    Orig
    0.42
    Athena
    0.41
    льної
    0.41
     holidays
    0.41
    Services
    0.40
    Cumm
    0.39
    ﻥ
    0.39
    Activations Density 0.008%

    No Known Activations