© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 225673
    Prev
    Next
    INDEX
    Explanations

    multilingual summarised information

    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_10_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
    <0xC2>
    0.48
     that
    0.48
     cuadr
    0.46
    ரு
    0.45
     and
    0.45
     می‌کنند
    0.43
    无
    0.43
     for
    0.42
     reac
    0.41
     “
    0.40
    POSITIVE LOGITS
     സര്‍ക്കാര്‍
    0.60
     μία
    0.52
     finalised
    0.52
     predsjed
    0.52
    ছাড়া
    0.52
     পেয়ে
    0.51
     summarised
    0.51
     Verbrauch
    0.50
    ):=\
    0.50
    }):=\
    0.50
    Activations Density 0.000%

    No Known Activations