© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53679
    Prev
    Next
    INDEX
    Explanations

    purr or paw

    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_55_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
     कक्क
    0.37
     Ern
    0.34
     TOC
    0.34
     geometry
    0.33
    हरण
    0.33
    acide
    0.33
     poet
    0.32
    ﭔ
    0.32
    損
    0.32
     اذ
    0.32
    POSITIVE LOGITS
     pur
    1.87
     paw
    1.81
     Paw
    1.59
    Pur
    1.59
     Pur
    1.58
    Paw
    1.57
    pur
    1.48
     paws
    1.41
    paw
    1.38
     PUR
    1.31
    Activations Density 0.002%

    No Known Activations