Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 261493
    Prev
    Next
    INDEX
    Explanations

    measurable results and success

    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_5_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
     in
    1.32
    </h2>
    0.90
     you
    0.86
    在
    0.83
    ের
    0.82
     yakin
    0.82
     onderdeel
    0.80
     নগর
    0.79
     fontFamily
    0.77
     hippocampus
    0.77
    POSITIVE LOGITS
    il
    1.65
    ли
    1.52
    د
    1.50
    c
    1.48
    n
    1.41
    a
    1.35
    an
    1.34
    ie
    1.34
    е
    1.30
    b
    1.26
    Activations Density 0.002%

    No Known Activations