© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138295
    Prev
    Next
    INDEX
    Explanations

    soap opera

    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_12_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
     BVHTree
    0.56
    ),]),
    0.55
    mData
    0.55
    <unused2163>
    0.55
    "，
    0.54
     PWMB
    0.54
    myCollision
    0.53
     اطلاع
    0.52
     সমস্যাবলী
    0.52
    rollerskates
    0.52
    POSITIVE LOGITS
     quiet
    0.57
     long
    0.53
     a
    0.52
     sintet
    0.51
    se
    0.50
     temperature
    0.50
     gel
    0.49
     gestation
    0.49
    he
    0.49
     einen
    0.49
    Activations Density 0.000%

    No Known Activations