© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 124737
    Prev
    Next
    INDEX
    Explanations

    distinctiveness

    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_3_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
    ה
    0.85
    も
    0.75
    ও
    0.71
    ری
    0.70
    ANT
    0.69
    </h3>
    0.68
    し
    0.67
    도
    0.67
    もら
    0.66
    ır
    0.65
    POSITIVE LOGITS
    是他
    0.57
     descuento
    0.57
     심
    0.56
    <0xA7>
    0.55
     malicious
    0.55
    ஞ்சு
    0.55
    TeXAtom
    0.54
    onimo
    0.54
     intér
    0.53
     limbo
    0.53
    Activations Density 0.001%

    No Known Activations