© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24569
    Prev
    Next
    INDEX
    Explanations

    punctuation and questions

    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_56_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
     ensure
    0.50
     -
    0.46
     ensuring
    0.44
     guarante
    0.43
     ensures
    0.42
    ″]
    0.39
     -,
    0.38
    “,
    0.38
     wh
    0.38
     responsable
    0.37
    POSITIVE LOGITS
     Above
    0.77
     Well
    0.64
     Have
    0.63
    Above
    0.63
     Few
    0.62
    Well
    0.59
    Few
    0.57
     Any
    0.56
    Have
    0.52
     Dont
    0.51
    Activations Density 0.011%

    No Known Activations