© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16973
    Prev
    Next
    INDEX
    Explanations

    politics and chemistry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
    ゐ
    0.42
     සිට
    0.40
    AssetName
    0.39
    从中
    0.38
    पाक
    0.38
    нить
    0.37
     ක්ර
    0.36
     })();
    0.36
    អ៊ី
    0.36
    cepter
    0.36
    POSITIVE LOGITS
     कहकर
    0.34
     sebesar
    0.34
     której
    0.33
     लहंगा
    0.33
    orange
    0.33
    ABEL
    0.33
    pounds
    0.33
     इन्वेस्ट
    0.33
    他又
    0.32
    myX
    0.32
    Activations Density 0.000%

    No Known Activations