© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44105
    Prev
    Next
    INDEX
    Explanations

    single

    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
     decía
    0.25
     Sony
    0.21
     copying
    0.21
     commended
    0.21
    斤
    0.21
    ígono
    0.21
     régi
    0.20
     módulos
    0.20
     murió
    0.20
     certificación
    0.20
    POSITIVE LOGITS
    Single
    0.28
     Single
    0.26
     single
    0.24
    单
    0.23
     SINGLE
    0.22
     enkelt
    0.22
    single
    0.22
    SINGLE
    0.19
     सिंगल
    0.19
     алма
    0.19
    Activations Density 0.035%

    No Known Activations