© 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. 214653
    Prev
    Next
    INDEX
    Explanations

    code and variables

    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
    तया
    0.36
    𝙠
    0.36
     ploy
    0.34
    коми
    0.33
    トゥ
    0.32
     पॉजिटिव
    0.32
     রাসেল
    0.31
    ໄວ
    0.31
    욧
    0.31
    𝚆
    0.31
    POSITIVE LOGITS
    း
    0.46
    िफिकेट
    0.43
    班牙
    0.42
    ್ಣ
    0.41
    ाया
    0.40
    xture
    0.39
    iguo
    0.38
    indrome
    0.38
    榈
    0.38
    饽
    0.37
    Activations Density 0.007%

    No Known Activations