© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141333
    Prev
    Next
    INDEX
    Explanations

    service life span and retirement

    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_12_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
     was
    0.64
    c
    0.64
     Diff
    0.60
    ).
    0.60
     F
    0.58
    _{
    0.58
     Ukraine
    0.58
    </h3>
    0.57
     Tam
    0.57
     U
    0.55
    POSITIVE LOGITS
     πρώτη
    0.67
     electrónica
    0.66
    وون
    0.66
    𝘯
    0.64
     употре
    0.63
     primeros
    0.63
    ون
    0.62
     첫
    0.62
     fotografías
    0.61
     electrónicos
    0.61
    Activations Density 0.000%

    No Known Activations