© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214346
    Prev
    Next
    INDEX
    Explanations

    ic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    heny
    0.38
    ométrique
    0.37
    ophenyl
    0.37
     morphologies
    0.37
    eyen
    0.37
     pedagogical
    0.36
    ଷ
    0.36
    餮
    0.36
    raquinone
    0.36
    ozen
    0.36
    POSITIVE LOGITS
     asa
    0.43
    xr
    0.43
     CRL
    0.41
     Maher
    0.40
    ivided
    0.39
     restre
    0.39
    ઠ
    0.39
     Crush
    0.38
    CCR
    0.38
     CCR
    0.38
    Activations Density 0.000%

    No Known Activations