© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6252
    Prev
    Next
    INDEX
    Explanations

    royal family, government, constitution, exile, palace

    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_39_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
     optimal
    0.41
     melting
    0.40
    굶
    0.39
     dolphin
    0.39
     bumble
    0.39
     idyllic
    0.38
    DIM
    0.38
     hive
    0.38
     b
    0.37
    ردم
    0.37
    POSITIVE LOGITS
    decor
    0.45
    Decor
    0.43
    饰
    0.43
    Gabriel
    0.40
    Joel
    0.40
    Dad
    0.38
    hose
    0.37
    擦
    0.37
    Sir
    0.37
    cous
    0.37
    Activations Density 0.028%

    No Known Activations