© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86945
    Prev
    Next
    INDEX
    Explanations

    where is

    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_23_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
    Ủ
    0.45
    PropertyList
    0.40
    RequestBuilder
    0.39
     Yarn
    0.39
    NFT
    0.38
    Connector
    0.37
    Alb
    0.37
    剑
    0.37
    Yam
    0.37
     வளர்
    0.36
    POSITIVE LOGITS
     bouncing
    0.49
     kicking
    0.46
    乑
    0.45
     we
    0.44
    sächlich
    0.43
    چھے
    0.41
     daisy
    0.40
     punitive
    0.40
     orange
    0.40
    ಃ
    0.40
    Activations Density 0.000%

    No Known Activations