© 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-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201553
    Prev
    Next
    INDEX
    Explanations

    stating upfront

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    Low
    0.56
    TRAN
    0.55
    ड
    0.55
    ...
    0.53
    DE
    0.53
    DH
    0.53
    ed
    0.52
    m
    0.51
    3
    0.50
    ээ
    0.50
    POSITIVE LOGITS
     Erica
    0.64
     figlio
    0.61
     ciò
    0.61
    pessoas
    0.58
     figli
    0.57
     ripet
    0.57
     it
    0.56
     tada
    0.56
     figlia
    0.54
     Maserati
    0.54
    Activations Density 0.001%

    No Known Activations