© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13115
    Prev
    Next
    INDEX
    Explanations

    colonialism, empire, historical periods, slavery

    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_13_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
    жник
    0.51
    Ρ
    0.51
    nR
    0.50
     정의역
    0.48
    Lung
    0.48
     संवै
    0.47
     alps
    0.46
    Τ
    0.46
     বিনি
    0.45
     ductility
    0.45
    POSITIVE LOGITS
     некоторых
    0.49
     других
    0.46
     Sy
    0.45
    </b>
    0.45
     काली
    0.43
    вав
    0.41
     संघर्ष
    0.41
     Shakespeare
    0.41
     Colonial
    0.41
     бы
    0.40
    Activations Density 0.022%

    No Known Activations