© 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. 6441
    Prev
    Next
    INDEX
    Explanations

    abstract processes and actions

    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
     Перейти
    0.56
    ेड
    0.53
     Atmospheric
    0.50
    denly
    0.50
    ました
    0.49
     Х
    0.49
    )}$,
    0.48
     Dessa
    0.48
     }^{+}$
    0.48
     Hitt
    0.48
    POSITIVE LOGITS
    FOUR
    0.57
    ෙන්
    0.56
    幅度
    0.56
     वालों
    0.56
    ͙
    0.55
     والك
    0.55
    もの
    0.54
     również
    0.53
    情绪
    0.53
    નુ
    0.53
    Activations Density 1.236%

    No Known Activations