© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92636
    Prev
    Next
    INDEX
    Explanations

    retaining, retained, retains, retention

    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_11_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
    ед
    0.61
    蜮
    0.59
    eniendo
    0.58
    m
    0.57
    meleri
    0.57
     wenigen
    0.55
    athi
    0.55
    કી
    0.55
    eseorang
    0.55
     anderes
    0.54
    POSITIVE LOGITS
     Be
    0.64
     I
    0.58
     úpl
    0.55
     SPSS
    0.53
    гия
    0.52
     Substance
    0.52
     pilot
    0.52
    რე
    0.52
     premiere
    0.51
    be
    0.50
    Activations Density 0.001%

    No Known Activations