© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37315
    Prev
    Next
    INDEX
    Explanations

    pro-democracy movements

    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_3_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
    an
    0.88
    dır
    0.69
    t
    0.60
    stays
    0.57
    <0xA3>
    0.56
    <0x93>
    0.55
    н
    0.55
    며
    0.55
    raient
    0.54
    os
    0.54
    POSITIVE LOGITS
    "
    0.91
     for
    0.88
     entour
    0.69
    h
    0.66
     mengh
    0.66
     y
    0.64
     applic
    0.64
     universit
    0.64
    ],
    0.63
    ”
    0.63
    Activations Density 0.004%

    No Known Activations