© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102262
    Prev
    Next
    INDEX
    Explanations

    Tagalog or foreign words

    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_16_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
    О
    0.57
    Over
    0.55
    Create
    0.55
    is
    0.52
    All
    0.51
    Current
    0.50
    Close
    0.50
    h
    0.50
    Mania
    0.50
    Soil
    0.50
    POSITIVE LOGITS
     पश्च
    0.46
     നഷ്ട
    0.45
    ched
    0.45
    जेक्ट
    0.45
    利益
    0.44
    防御
    0.44
    ovost
    0.44
    ierten
    0.44
     chaud
    0.43
     ngôn
    0.43
    Activations Density 0.000%

    No Known Activations