© 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. 4861
    Prev
    Next
    INDEX
    Explanations

    trigonometry and trivial truths

    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
    u
    2.31
    Denote
    2.26
     milder
    2.13
    ある
    2.13
     tandem
    2.12
    riches
    2.10
     вниз
    2.10
     approximated
    2.07
    pkl
    2.06
     afar
    2.05
    POSITIVE LOGITS
    ശാസ്ത്ര
    2.55
    gment
    2.31
     verbose
    2.26
     bine
    2.23
    й
    2.23
     distributive
    2.09
    𝘯
    2.07
    𝘦
    2.06
    וס
    2.02
    де
    2.00
    Activations Density 0.016%

    No Known Activations