© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90122
    Prev
    Next
    INDEX
    Explanations

    twist or twisted

    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_11_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
    ে
    0.63
     ře
    0.61
     twink
    0.57
     shards
    0.55
     přes
    0.53
    க்ஸாண்ட
    0.52
    l
    0.52
    ี
    0.52
    𝚕
    0.52
     göra
    0.52
    POSITIVE LOGITS
    5
    0.73
     and
    0.70
    ando
    0.66
    8
    0.66
     आणि
    0.65
    9
    0.64
     for
    0.64
     Nossa
    0.64
    6
    0.64
    {
    0.62
    Activations Density 0.002%

    No Known Activations