© 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. 6104
    Prev
    Next
    INDEX
    Explanations

    path delimiters

    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
    й
    2.22
     Tatsache
    2.09
    ${
    2.09
     granularity
    2.05
     pondered
    2.05
     khả
    2.04
    쩍
    2.04
     locator
    2.04
     срок
    2.04
     frug
    2.03
    POSITIVE LOGITS
    ot
    2.05
    вання
    2.00
    된
    1.93
    Р
    1.92
    bodies
    1.91
    furan
    1.89
    𝘬
    1.87
     Certainly
    1.87
    ques
    1.86
     rightly
    1.86
    Activations Density 0.000%

    No Known Activations