© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5775
    Prev
    Next
    INDEX
    Explanations

    qualified tutors, young talent, mean fox, senior, elderly woman

    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_3_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
    y
    0.74
    限り
    0.63
    camb
    0.60
     میشه
    0.59
    inking
    0.58
    ﻕ
    0.58
    chung
    0.58
    epic
    0.56
    ingly
    0.55
    nPlease
    0.55
    POSITIVE LOGITS
    нов
    0.72
    いない
    0.68
    傅
    0.67
    字幕
    0.67
    
    0.67
    ͊
    0.65
     craftsmen
    0.64
     hairdry
    0.63
    με
    0.63
     своему
    0.62
    Activations Density 0.325%

    No Known Activations