© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51855
    Prev
    Next
    INDEX
    Explanations

    exciting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    ška
    0.45
    шк
    0.38
    šk
    0.36
    ᱡ
    0.35
    šku
    0.34
    cevam
    0.34
    erevan
    0.34
    𝕚
    0.34
     रस
    0.34
    bgcolor
    0.34
    POSITIVE LOGITS
     exhilarating
    0.47
    UCK
    0.46
    刺激
    0.41
     polarised
    0.40
     तनु
    0.40
     thrilling
    0.39
     printable
    0.39
     enthr
    0.39
    лед
    0.38
     exciting
    0.38
    Activations Density 0.000%

    No Known Activations