© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212363
    Prev
    Next
    INDEX
    Explanations

    Cultural Heritage Preservation and Management

    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_5_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
     (
    1.89
     in
    1.78
    ן
    1.67
    리
    1.44
     been
    1.42
    ন
    1.42
    ن
    1.41
    শালী
    1.38
     by
    1.37
     در
    1.37
    POSITIVE LOGITS
    t
    1.30
    ين
    1.30
    í
    1.23
    l
    1.16
    你
    1.09
    おしゃれ
    1.08
    ey
    1.04
    arro
    1.02
    en
    1.02
    ą
    0.96
    Activations Density 0.001%

    No Known Activations