© 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. 5998
    Prev
    Next
    INDEX
    Explanations

    software platforms and services

    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
    𝘮
    2.38
    с
    2.33
    ل
    2.32
    wid
    2.32
    ي
    2.32
    म
    2.27
    一方で
    2.22
    ح
    2.22
    স
    2.18
     sucede
    2.14
    POSITIVE LOGITS
     allError
    1.85
     fortunes
    1.82
    }^{
    1.67
     Verarbeitung
    1.64
    ᴛ
    1.60
     Hercules
    1.57
     tempHeader
    1.54
     часу
    1.53
    ्ट
    1.52
    }};
    1.52
    Activations Density 0.089%

    No Known Activations