© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61564
    Prev
    Next
    INDEX
    Explanations

    critical stopping volume collective behaviour

    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_11_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
    WithError
    0.45
    ভিড
    0.45
     連
    0.44
     बीएड
    0.44
     设计
    0.44
    '،
    0.44
     Generation
    0.43
     আশ
    0.42
     generación
    0.41
     Design
    0.41
    POSITIVE LOGITS
    aktual
    0.53
    Nem
    0.52
     [
    0.51
    팟
    0.51
     lorsqu
    0.50
     :
    0.49
     plong
    0.48
    ข
    0.48
    immutable
    0.47
     NEM
    0.47
    Activations Density 0.005%

    No Known Activations