© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37208
    Prev
    Next
    INDEX
    Explanations

    Lithuanian text

    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_57_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
     gust
    0.40
     Panch
    0.38
     пан
    0.38
    坏
    0.37
     rei
    0.37
     सुशील
    0.36
     neuropath
    0.36
     மாய
    0.36
    usam
    0.36
    ੈ
    0.36
    POSITIVE LOGITS
     sprouted
    0.46
    isku
    0.41
    inese
    0.41
    dzi
    0.39
    Lov
    0.39
    ziu
    0.39
     ji
    0.37
     za
    0.36
     housekeeping
    0.36
     Lov
    0.36
    Activations Density 0.000%

    No Known Activations