© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168531
    Prev
    Next
    INDEX
    Explanations

    und

    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
     d
    0.56
     De
    0.45
    De
    0.44
     indicated
    0.42
     الده
    0.41
    Tout
    0.40
     recognised
    0.38
     د
    0.36
     succinct
    0.36
     apparent
    0.36
    POSITIVE LOGITS
    dig
    0.67
     digging
    0.54
     Dig
    0.53
    Dig
    0.53
     dig
    0.52
     digs
    0.47
     Digi
    0.43
    ึง
    0.40
    ടുത്ത
    0.40
     dug
    0.39
    Activations Density 0.000%

    No Known Activations