© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37290
    Prev
    Next
    INDEX
    Explanations

    American titles and cultural references

    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
    CET
    0.63
    ي
    0.62
    AL
    0.59
    PQ
    0.57
    LTE
    0.56
     effiz
    0.56
     It
    0.55
     ايجاد
    0.54
     nahilalakip
    0.54
    Y
    0.53
    POSITIVE LOGITS
    s
    0.76
     (
    0.74
    0.63
    cal
    0.63
    sm
    0.63
    mc
    0.59
    ের
    0.58
    ंद
    0.58
    ओं
    0.58
    nd
    0.56
    Activations Density 0.001%

    No Known Activations