© 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. 6237
    Prev
    Next
    INDEX
    Explanations

    reflection

    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
    ती
    2.74
    ities
    2.71
     berper
    2.64
    ख
    2.61
     парламент
    2.50
    ﻭ
    2.49
    وْ
    2.48
    ﺏ
    2.44
    ियन
    2.39
    См
    2.37
    POSITIVE LOGITS
    ively
    2.92
    ivity
    2.70
    ように
    2.65
    ようになりました
    2.58
    ようになって
    2.56
    operatorname
    2.49
    多い
    2.46
     abrang
    2.38
     hoop
    2.37
    鹉
    2.37
    Activations Density 0.046%

    No Known Activations