© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249300
    Prev
    Next
    INDEX
    Explanations

    dis

    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_56_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
     conv
    0.50
     validated
    0.45
    説
    0.43
     Conv
    0.42
     첨
    0.41
    Conv
    0.40
     looked
    0.39
     설
    0.39
    つけ
    0.39
    conv
    0.38
    POSITIVE LOGITS
    pr
    0.52
     pr
    0.50
    пру
    0.49
    ph
    0.48
    Credits
    0.45
    pu
    0.44
     प्रतिसाद
    0.44
    <0x89>
    0.44
    credit
    0.44
     credited
    0.43
    Activations Density 0.000%

    No Known Activations