© 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. 89187
    Prev
    Next
    INDEX
    Explanations

    needed rainfall, time, relief, economic, bona fide

    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
    w
    0.69
    Unsere
    0.68
    July
    0.66
     july
    0.66
     July
    0.63
     meie
    0.62
     Y
    0.60
     insectes
    0.60
    June
    0.57
     juillet
    0.57
    POSITIVE LOGITS
     выходит
    0.59
    或
    0.59
    cular
    0.54
    ется
    0.54
    ackBar
    0.53
     end
    0.52
     out
    0.51
    cia
    0.51
     deliberately
    0.50
     लेकर
    0.50
    Activations Density 0.000%

    No Known Activations