© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9350
    Prev
    Next
    INDEX
    Explanations

    yeah, followed by punctuation

    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_13_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
    άζ
    0.29
    inear
    0.27
     Ấn
    0.27
    ()">
    0.26
    embers
    0.26
     सुधा
    0.26
    ά
    0.26
    आती
    0.26
    𝕊
    0.25
    lossen
    0.25
    POSITIVE LOGITS
    文
    0.28
    content
    0.24
    माल
    0.24
    weh
    0.23
     yak
    0.23
    auge
    0.23
     scient
    0.22
    題目
    0.22
    deployment
    0.21
     bloke
    0.21
    Activations Density 0.014%

    No Known Activations