© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4427
    Prev
    Next
    INDEX
    Explanations

    code attributes and events

    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_38_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
     scala
    0.38
     greet
    0.36
     Tackle
    0.36
     Cake
    0.35
    Passive
    0.35
    ocin
    0.35
    嬸
    0.35
     cake
    0.34
     behand
    0.34
     w
    0.34
    POSITIVE LOGITS
     spider
    0.45
     ktorá
    0.42
     Parenting
    0.42
     юм
    0.42
     sigurn
    0.41
    тики
    0.40
    Corona
    0.40
     parenting
    0.40
     बिग
    0.40
    colm
    0.40
    Activations Density 0.021%

    No Known Activations