© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    recursive vs iterative

    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
    zmdi
    0.66
     ¡
    0.63
    这座
    0.63
    лән
    0.60
    ResourceType
    0.59
     испол
    0.59
     donn
    0.59
     wr
    0.58
     gre
    0.58
    格兰
    0.58
    POSITIVE LOGITS
    д
    0.78
    ла
    0.67
    a
    0.59
    o
    0.57
    deficient
    0.57
    ির
    0.56
    닉
    0.55
    नव
    0.54
    Hel
    0.54
     gange
    0.54
    Activations Density 0.014%

    No Known Activations