© 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. 124212
    Prev
    Next
    INDEX
    Explanations

    Albert Bierstadt, Al Green, Almorox, Almere

    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
     is
    0.71
    
    0.67
    se
    0.67
    ي
    0.65
    ૭
    0.63
    ות
    0.63
    라
    0.63
    ci
    0.61
    ла
    0.61
     Parigi
    0.61
    POSITIVE LOGITS
    1
    0.75
     competit
    0.70
    at
    0.63
     установ
    0.59
    ικ
    0.57
    it
    0.57
    وم
    0.57
    на
    0.56
    up
    0.55
    ков
    0.55
    Activations Density 0.000%

    No Known Activations