© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62062
    Prev
    Next
    INDEX
    Explanations

    Pi

    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_59_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
     PI
    2.34
     piet
    2.28
     Piet
    2.06
    PI
    2.00
     pied
    1.96
     Pied
    1.90
     π
    1.88
     пі
    1.88
     pi
    1.85
     پی
    1.80
    POSITIVE LOGITS
    P
    0.42
    ப்
    0.38
    spam
    0.36
    MaxPooling
    0.34
    ър
    0.34
     curls
    0.34
    ানো
    0.33
    ící
    0.32
    LDL
    0.32
    ப்பத
    0.32
    Activations Density 0.045%

    No Known Activations