© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3315
    Prev
    Next
    INDEX
    Explanations

    i in code loops

    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_5_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
     уж
    0.68
    𝘨
    0.65
     amigos
    0.65
     вот
    0.64
     années
    0.63
    𝗡
    0.62
     éventuellement
    0.61
     eigentlich
    0.61
     buen
    0.61
    yh
    0.61
    POSITIVE LOGITS
    ো
    0.71
     Sleeve
    0.69
    е
    0.68
    ណ៌
    0.67
    kje
    0.66
     opportun
    0.66
    ătoare
    0.64
    ో
    0.63
     caters
    0.63
    Ꮈ
    0.62
    Activations Density 0.058%

    No Known Activations