© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12744
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     SCS
    0.38
    dec
    0.36
     फ्रांस
    0.36
    decision
    0.36
    %(
    0.35
    Nature
    0.35
    Eg
    0.35
     étudiants
    0.34
    conduct
    0.33
    Conduct
    0.33
    POSITIVE LOGITS
    izable
    0.48
     dinyatakan
    0.42
    issory
    0.41
    MsgCallBack
    0.40
    DrawerToggle
    0.40
    保
    0.40
    Palette
    0.39
    astri
    0.39
    نامہ
    0.38
     बाती
    0.38
    Activations Density 0.000%

    No Known Activations