© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    export class

    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
     absenteeism
    1.92
     rugged
    1.74
    անի
    1.71
    ongoing
    1.66
     surprising
    1.65
     impressive
    1.63
    ️
    1.63
     wiper
    1.62
     jokingly
    1.61
     Sandia
    1.61
    POSITIVE LOGITS
    te
    1.49
    nt
    1.43
    此之外
    1.39
    r
    1.37
     lineare
    1.28
     însă
    1.28
    এছ
    1.27
    ده
    1.27
    𝒐
    1.26
    IP
    1.25
    Activations Density 0.001%

    No Known Activations