© 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. 23035
    Prev
    Next
    INDEX
    Explanations

    ph

    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
     wording
    1.16
     phrasing
    1.04
     worded
    0.98
     phr
    0.65
    秚
    0.40
     भर्तियों
    0.37
    ˙
    0.37
    ैसे
    0.37
    STEIN
    0.37
     stockno
    0.36
    POSITIVE LOGITS
     W
    1.48
     ph
    1.45
     Ph
    1.38
    w
    1.33
    W
    1.30
    Ph
    1.13
    表
    1.10
    ph
    1.03
     w
    1.00
    Ｗ
    0.90
    Activations Density 0.053%

    No Known Activations