© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210382
    Prev
    Next
    INDEX
    Explanations

    cities in India and Spain

    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_20_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
     shortcuts
    0.34
     defunct
    0.34
    身份
    0.34
     tilbage
    0.34
     spät
    0.33
    Ź
    0.33
     источ
    0.33
     кілька
    0.32
     powodu
    0.32
    ুয়ার
    0.32
    POSITIVE LOGITS
    jaa
    0.41
    anded
    0.37
    dea
    0.37
    ille
    0.36
    anser
    0.36
    🦵
    0.36
    elajaran
    0.36
    ksi
    0.35
    jada
    0.35
    স্থ
    0.35
    Activations Density 0.001%

    No Known Activations