© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37998
    Prev
    Next
    INDEX
    Explanations

    german cities and states

    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_11_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
     fintech
    0.58
    е
    0.58
     metaphorical
    0.57
    ");
    0.56
    ед
    0.55
    "
    0.55
    ેટ
    0.53
    ...");
    0.53
     clapping
    0.53
     dense
    0.52
    POSITIVE LOGITS
    Germany
    0.66
    German
    0.66
     독일
    0.63
     Duitse
    0.61
     Jerman
    0.59
     niemie
    0.58
     Duits
    0.58
     Германия
    0.58
     Germany
    0.57
     Германии
    0.57
    Activations Density 0.048%

    No Known Activations