© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205179
    Prev
    Next
    INDEX
    Explanations

    Q

    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_46_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
    槌
    0.38
    兀
    0.37
     બંધ
    0.37
     Gotham
    0.35
    ந்தை
    0.34
     தமிழர்
    0.34
    ার্
    0.34
    ᡠ
    0.34
    pload
    0.33
     बाजारों
    0.33
    POSITIVE LOGITS
     Q
    2.92
    Q
    2.66
    Ｑ
    2.02
    𝑄
    1.88
     الق
    1.87
     q
    1.61
    Qs
    1.52
     क्यू
    1.48
     Qo
    1.42
     Qe
    1.38
    Activations Density 0.001%

    No Known Activations