© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155253
    Prev
    Next
    INDEX
    Explanations

    sphere

    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_50_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
     मिताली
    0.39
    ektion
    0.38
    edown
    0.37
     Bole
    0.37
     riman
    0.37
     lawmaker
    0.36
     lawmakers
    0.35
    ᴰ
    0.35
     dissol
    0.35
     Ν
    0.35
    POSITIVE LOGITS
     sphere
    1.34
     Sphere
    1.33
    Sphere
    1.30
    sphere
    1.30
    Sph
    1.25
     স্প
    1.22
     sph
    1.21
    Spencer
    1.21
     Sph
    1.19
     Spencer
    1.17
    Activations Density 0.010%

    No Known Activations