© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33903
    Prev
    Next
    INDEX
    Explanations

    again

    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_50_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
    ো
    0.59
    ोज
    0.53
    ोजा
    0.47
    ist
    0.44
    ौती
    0.43
    がる
    0.41
    ტორი
    0.40
    ("//
    0.38
    ierungs
    0.38
    holt
    0.38
    POSITIVE LOGITS
     again
    1.77
    again
    1.68
    Again
    1.63
     Again
    1.56
     AGAIN
    1.38
     novamente
    1.34
     nuevamente
    1.30
     wieder
    1.30
     igjen
    1.28
     опять
    1.25
    Activations Density 0.002%

    No Known Activations