© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6850
    Prev
    Next
    INDEX
    Explanations

    mailman or ax variants (MIT)

    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
    ใจ
    0.70
    u
    0.67
    am
    0.66
    лся
    0.64
    el
    0.61
    ্থ
    0.61
    us
    0.60
    is
    0.59
    ある
    0.59
    amaks
    0.58
    POSITIVE LOGITS
    ला
    0.70
    イ
    0.64
     Pursuant
    0.63
     используют
    0.63
     mouth
    0.62
    жек
    0.61
    ዀ
    0.61
    வச
    0.60
     aback
    0.58
     EXEMPL
    0.58
    Activations Density 0.005%

    No Known Activations