© 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. 215881
    Prev
    Next
    INDEX
    Explanations

    say "p" words

    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
    炇
    0.46
    িষ
    0.43
     Metcalf
    0.40
    meli
    0.40
     }(\
    0.39
    䅡
    0.39
     helic
    0.38
     Jij
    0.38
    เจ
    0.37
    㴌
    0.36
    POSITIVE LOGITS
     pants
    2.45
     pant
    2.44
    Pant
    2.42
     Pant
    2.36
     Pants
    2.34
    pant
    2.25
    pants
    2.14
    パンツ
    1.92
     pantal
    1.84
    裤
    1.83
    Activations Density 0.000%

    No Known Activations