© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203154
    Prev
    Next
    INDEX
    Explanations

    it was no use

    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_12_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
     डूब
    0.67
     l
    0.61
    i
    0.60
     כ
    0.59
     moda
    0.58
     בע
    0.58
     entrust
    0.58
     ос
    0.55
     do
    0.55
     contempl
    0.54
    POSITIVE LOGITS
    {
    0.73
    loa
    0.64
     Angebote
    0.54
     सत्यापित
    0.54
    la
    0.53
    lo
    0.53
    measuredangle
    0.53
     Roast
    0.52
     почвы
    0.51
     einige
    0.50
    Activations Density 0.000%

    No Known Activations