© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138753
    Prev
    Next
    INDEX
    Explanations

    programming

    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
     Simon
    0.44
     PFS
    0.43
     swing
    0.41
    نامج
    0.40
     Swing
    0.39
    ᅴ
    0.39
    Simon
    0.39
    珊
    0.39
     participan
    0.38
     பொருள்
    0.38
    POSITIVE LOGITS
     डो
    0.39
     leaner
    0.38
    芠
    0.38
    起來
    0.37
    螃
    0.36
     cellular
    0.35
     đô
    0.35
     עצ
    0.35
     ")
    0.34
     потре
    0.34
    Activations Density 0.001%

    No Known Activations