© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109164
    Prev
    Next
    INDEX
    Explanations

    Kowalski, Leonard, bone

    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_1_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
    к
    1.52
    ía
    1.16
    ón
    1.10
    ூர்
    1.05
    äure
    1.02
     rehabilitación
    1.00
    ían
    0.99
    ó
    0.98
     cirugía
    0.97
     две
    0.97
    POSITIVE LOGITS
    0
    1.60
    2
    1.59
    ו
    1.47
    the
    1.38
    고
    1.20
    8
    1.12
    На
    1.11
    و
    1.06
    tors
    1.05
    К
    1.05
    Activations Density 0.000%

    No Known Activations