© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22590
    Prev
    Next
    INDEX
    Explanations

    Filipino words

    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_56_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
     dug
    0.37
     ስለዚህ
    0.37
    ーション
    0.36
     तुलसी
    0.36
    ّم
    0.36
     Tul
    0.36
    掐
    0.36
     Na
    0.36
     Address
    0.36
     मुल
    0.36
    POSITIVE LOGITS
     may
    0.46
     magn
    0.42
    Magn
    0.39
     Magn
    0.37
    magn
    0.37
    лег
    0.36
    may
    0.36
     magg
    0.36
     magas
    0.36
     seas
    0.36
    Activations Density 0.001%

    No Known Activations