© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167965
    Prev
    Next
    INDEX
    Explanations

    flies and fly

    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_34_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
     seab
    0.45
     crustaceans
    0.44
     seven
    0.43
     Seab
    0.41
     sea
    0.40
     patrol
    0.40
     البحر
    0.39
    捡
    0.39
     six
    0.38
     Seven
    0.38
    POSITIVE LOGITS
     прад
    0.46
    uates
    0.40
    incre
    0.39
    raphics
    0.37
    ="<%=
    0.37
    outstanding
    0.37
    ेच्छा
    0.36
    itsi
    0.36
     confond
    0.36
     Бан
    0.36
    Activations Density 0.000%

    No Known Activations