© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5176
    Prev
    Next
    INDEX
    Explanations

    fields, required, optional

    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_38_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
    iaio
    0.40
    蚯
    0.38
    methoxy
    0.38
    ⇉
    0.36
    كاته
    0.36
    ieron
    0.36
    icho
    0.36
    rxjs
    0.36
    ịnh
    0.36
    >∕</
    0.36
    POSITIVE LOGITS
     fields
    2.39
     field
    2.16
    字段
    1.99
     Fields
    1.98
    fields
    1.95
     campos
    1.90
    Fields
    1.88
     campo
    1.88
     поле
    1.81
    field
    1.77
    Activations Density 0.375%

    No Known Activations