© 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. 12498
    Prev
    Next
    INDEX
    Explanations

    code structuring 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_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
    entery
    0.07
     पर्व
    0.07
    릉
    0.06
    iggers
    0.06
     ensured
    0.06
     मणिपुर
    0.06
    িয়াছিলেন
    0.06
    াম
    0.06
     ensures
    0.06
    স্বর
    0.06
    POSITIVE LOGITS
    ድ
    0.08
    Private
    0.07
     можливість
    0.07
     λ
    0.07
     PRIVATE
    0.07
     možnost
    0.07
    Rel
    0.06
     широ
    0.06
     Completely
    0.06
     требований
    0.06
    Activations Density 0.088%

    No Known Activations