© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32334
    Prev
    Next
    INDEX
    Explanations

    technical improvements and implementations

    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_31_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
    昉
    0.39
    PushMatrix
    0.38
    RUNTIME
    0.38
    Loans
    0.38
    ्ठा
    0.38
    销量
    0.38
    inations
    0.37
     itemscope
    0.37
    倬
    0.37
     Copern
    0.37
    POSITIVE LOGITS
     alterations
    0.44
     gelişt
    0.44
     installation
    0.40
    ꒷
    0.40
     instalação
    0.40
     oprav
    0.39
     alteration
    0.39
    改造
    0.39
     установка
    0.39
     infrastructure
    0.39
    Activations Density 0.058%

    No Known Activations