© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171612
    Prev
    Next
    INDEX
    Explanations

    from that onward

    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_20_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
     더욱
    0.49
     حتى
    0.44
     『
    0.42
     テレビ
    0.42
     앞으로
    0.42
    ivin
    0.41
     ہو
    0.41
    콩
    0.41
     başına
    0.40
    ður
    0.40
    POSITIVE LOGITS
    sending
    0.45
     Sends
    0.41
     nach
    0.39
     ಸಮಯದಲ್ಲಿ
    0.39
     SWT
    0.38
    आपने
    0.38
     we
    0.37
     somebody
    0.37
     sending
    0.37
    anda
    0.36
    Activations Density 0.004%

    No Known Activations