© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7896
    Prev
    Next
    INDEX
    Explanations

    correct grammar and sentences

    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
    HING
    2.59
    er
    2.44
    zeuge
    2.27
     jih
    2.26
    >|</
    2.25
     vist
    2.23
     Είναι
    2.20
    ер
    2.19
    ни
    2.17
    紝
    2.15
    POSITIVE LOGITS
    و
    2.44
    ie
    2.33
    ж
    2.30
    {\
    2.30
    ঠিত
    2.23
    ermott
    2.12
     nucleotide
    2.09
    vo
    2.09
    رت
    2.06
     불구하고
    2.03
    Activations Density 0.103%

    No Known Activations