© 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. 45095
    Prev
    Next
    INDEX
    Explanations

    British Mandate Palestine

    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
     Bolívar
    0.54
    “
    0.50
     portée
    0.47
     निरीक्षण
    0.46
     ‘
    0.46
    羹
    0.45
     оси
    0.44
     lèvres
    0.44
     obstáculos
    0.44
    琵
    0.44
    POSITIVE LOGITS
     must
    0.48
     ash
    0.45
     products
    0.45
    ten
    0.44
     linen
    0.44
     চৈ
    0.44
     Chrome
    0.42
     we
    0.42
    ashing
    0.42
    in
    0.42
    Activations Density 0.003%

    No Known Activations