© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57877
    Prev
    Next
    INDEX
    Explanations

    boost economy or stocks

    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_11_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
    ح
    0.71
    الس
    0.68
     Cualquier
    0.64
    اب
    0.62
    cómo
    0.61
    其他
    0.61
    𝙤
    0.61
    дт
    0.60
    Как
    0.60
    राज्य
    0.60
    POSITIVE LOGITS
    ’
    0.62
     naïve
    0.61
     medico
    0.56
     superfluous
    0.56
    ній
    0.55
     carn
    0.55
     establish
    0.54
     priori
    0.54
    line
    0.53
    riz
    0.52
    Activations Density 0.002%

    No Known Activations