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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260945
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     Temperaturen
    1.29
    ઉસ
    1.07
    양
    1.06
     prochains
    1.04
    anci
    1.02
     vendas
    1.02
     ఆహ
    1.01
     اصل
    1.00
    एफटी
    0.98
     проис
    0.98
    POSITIVE LOGITS
     pornography
    1.27
     godiš
    1.18
    гне
    1.17
     wspól
    1.16
    ۟
    1.14
    ﻷ
    1.13
    ோருக்கு
    1.12
    lying
    1.12
    लेरिया
    1.11
     excuses
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.