© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42968
    Prev
    Next
    INDEX
    Explanations

    uric acid or reverse

    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_22_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
    μένα
    0.16
    ීන්
    0.15
    прода
    0.15
    लब
    0.15
     dewasa
    0.15
    리지
    0.14
     Erwachsene
    0.14
    ཉ
    0.14
    ᓯ
    0.14
     nucleic
    0.14
    POSITIVE LOGITS
    defineProperty
    0.18
     سقوط
    0.17
     पृथ्वी
    0.17
     unquestionably
    0.17
    ≦
    0.17
    劾
    0.17
     Gemä
    0.16
     subdiv
    0.16
    tBleStatus
    0.16
     PSOE
    0.16
    Activations Density 0.000%

    No Known Activations