© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174553
    Prev
    Next
    INDEX
    Explanations

    prices increase

    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_20_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
     영역
    0.26
    [])
    0.24
     방법
    0.24
    方式
    0.23
    UR
    0.23
    Zur
    0.23
    Either
    0.22
    おく
    0.22
    能力的
    0.22
     개념
    0.22
    POSITIVE LOGITS
     Andal
    0.29
    --',
    0.27
     mildly
    0.26
     amerikan
    0.25
    izate
    0.25
     condesc
    0.25
     mild
    0.24
     Americans
    0.24
     Amerikan
    0.24
     Asturias
    0.23
    Activations Density 0.003%

    No Known Activations