© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203435
    Prev
    Next
    INDEX
    Explanations

    famous places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    knee
    0.44
    ewords
    0.42
    egd
    0.41
    extremely
    0.41
     செயல்
    0.39
     весьма
    0.39
     ()=>{
    0.38
     Bentham
    0.38
     досить
    0.38
    𝔦
    0.36
    POSITIVE LOGITS
     adorned
    0.45
     matched
    0.44
     vernacular
    0.44
     Oncology
    0.40
     Add
    0.39
     offering
    0.38
     updating
    0.38
     draped
    0.38
     метро
    0.37
     UPDATE
    0.37
    Activations Density 0.003%

    No Known Activations