© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14889
    Prev
    Next
    INDEX
    Explanations

    input validation and output encoding

    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_40_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
    Cha
    0.44
     Cha
    0.41
    ೀರ್
    0.40
    pipelines
    0.39
    Ni
    0.38
     vie
    0.37
    Vie
    0.37
    澀
    0.37
     rail
    0.37
     Shil
    0.36
    POSITIVE LOGITS
    auto
    0.48
     encoding
    0.48
     autof
    0.46
     auto
    0.45
    encoding
    0.44
    block
    0.44
    Auto
    0.44
     blok
    0.43
     block
    0.42
     Auto
    0.42
    Activations Density 0.042%

    No Known Activations