© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6512
    Prev
    Next
    INDEX
    Explanations

    `ang` sound, end of word

    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
    اً
    3.19
    giveness
    2.71
    تی
    2.59
    в
    2.57
     доступа
    2.56
     spinel
    2.54
     perturbative
    2.53
     intermedia
    2.52
    lighting
    2.50
    제
    2.45
    POSITIVE LOGITS
    ﻲ
    2.58
    деся
    2.54
    ak
    2.21
     इसमें
    2.19
     tiba
    2.18
    ick
    2.17
    会在
    2.09
    erst
    2.08
    as
    2.08
    
    2.07
    Activations Density 0.002%

    No Known Activations