© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88205
    Prev
    Next
    INDEX
    Explanations

    German place names

    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_3_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
    ’;
    0.69
    {
    0.69
     şekilde
    0.63
     የመጀመሪያ
    0.61
     に
    0.61
    да
    0.60
     मुनाफा
    0.59
    ");
    0.58
    është
    0.58
     eminently
    0.58
    POSITIVE LOGITS
    is
    1.09
    w
    0.88
    h
    0.76
    isn
    0.75
    re
    0.73
    ad
    0.72
    리
    0.71
    ிற
    0.71
    c
    0.71
     Into
    0.70
    Activations Density 0.000%

    No Known Activations