© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80679
    Prev
    Next
    INDEX
    Explanations

    judged by somebody

    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_0_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
    л
    1.69
    നിന്ന്
    1.34
     and
    1.32
    ため
    1.32
    ني
    1.31
    ado
    1.26
    जिसे
    1.24
     at
    1.20
    نی
    1.19
     ﺍ
    1.18
    POSITIVE LOGITS
    ه
    1.98
    و
    1.83
    a
    1.75
    ו
    1.66
    。
    1.64
    ا
    1.63
    س
    1.59
    )
    1.52
    {
    1.52
    )。
    1.51
    Activations Density 0.000%

    No Known Activations