© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217208
    Prev
    Next
    INDEX
    Explanations

    receiving party or equilibrium thermodynamics

    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_16_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
    pperware
    0.57
    \%,
    0.56
     ಎರಡು
    0.55
    xRt
    0.55
     obtenue
    0.55
     }%
    0.54
    urètre
    0.54
     አንድ
    0.54
     positifs
    0.54
    *\
    0.53
    POSITIVE LOGITS
    ↵
    0.61
     text
    0.54
    t
    0.53
     Mexican
    0.49
     Level
    0.48
     modernization
    0.48
    o
    0.47
     null
    0.47
    c
    0.47
     DC
    0.46
    Activations Density 0.000%

    No Known Activations