© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3404
    Prev
    Next
    INDEX
    Explanations

    those who / those around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    я
    1.29
    an
    1.17
    ます
    1.15
    finn
    1.08
    وما
    1.04
    ﻕ
    1.04
    ượng
    1.03
     न्यून
    1.02
     zdroj
    1.01
     quale
    1.00
    POSITIVE LOGITS
    на
    1.47
    न
    1.35
    𝘂
    1.29
    
    1.27
    ೇತ್ರ
    1.25
     числе
    1.24
    𝗗
    1.22
     карта
    1.21
    தள
    1.20
    
    1.20
    Activations Density 0.047%

    No Known Activations