© 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. 169812
    Prev
    Next
    INDEX
    Explanations

    the letter p

    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
    羨
    0.36
     piecewise
    0.35
     Derbyshire
    0.35
     pierce
    0.35
    ге
    0.34
     bhfu
    0.33
    நக
    0.32
    internalType
    0.32
    ВС
    0.32
    ín
    0.32
    POSITIVE LOGITS
    p
    1.99
    P
    1.83
     প
    1.60
     p
    1.43
     پ
    1.42
     P
    1.30
    <0x89>
    1.28
     प
    1.27
    setP
    1.27
    พ
    1.20
    Activations Density 0.070%

    No Known Activations