© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205931
    Prev
    Next
    INDEX
    Explanations

    space elevators and solar power ventures

    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_20_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
    涟
    0.42
     accep
    0.41
     acceptance
    0.41
    там
    0.41
     femininity
    0.41
     отмети
    0.40
     مقابل
    0.40
    ieni
    0.39
     кожного
    0.39
     bouts
    0.38
    POSITIVE LOGITS
     venture
    0.54
    Aid
    0.49
    তরাং
    0.46
    )^{-\
    0.46
    venture
    0.46
     Venture
    0.45
    initiative
    0.44
    project
    0.41
    CreateCharacter
    0.41
    नाथन
    0.41
    Activations Density 0.000%

    No Known Activations