© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137160
    Prev
    Next
    INDEX
    Explanations

    Spanish words indicating existence

    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_12_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
    न
    0.49
    ccoli
    0.40
    आ
    0.39
    н
    0.39
    创新
    0.38
    াইন
    0.38
    וף
    0.38
    ن
    0.38
    igliano
    0.38
    Abstraction
    0.38
    POSITIVE LOGITS
     stå
    0.46
     непло
    0.45
     Wolves
    0.43
    هِ
    0.43
     Merced
    0.43
    ões
    0.42
    мы
    0.42
    <0xA0>
    0.41
     că
    0.41
     pokud
    0.41
    Activations Density 0.001%

    No Known Activations