© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85941
    Prev
    Next
    INDEX
    Explanations

    biomolecules

    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_3_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
     individ
    0.73
     tende
    0.73
     inciner
    0.71
     будет
    0.68
     riscos
    0.67
     accede
    0.66
     в
    0.66
    ﻦ
    0.66
     individuales
    0.65
     itp
    0.65
    POSITIVE LOGITS
    V
    0.89
    A
    0.87
    L
    0.81
    se
    0.77
    G
    0.73
    Ad
    0.71
    C
    0.69
    1
    0.67
    B
    0.65
    di
    0.63
    Activations Density 0.000%

    No Known Activations