© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86521
    Prev
    Next
    INDEX
    Explanations

    Amazon Redshift Web Services

    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_3_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
    ib
    0.70
    X
    0.70
    l
    0.67
    g
    0.66
    R
    0.64
    vention
    0.62
    &
    0.60
    og
    0.59
    cept
    0.58
    cent
    0.58
    POSITIVE LOGITS
    :
    0.79
     to
    0.79
     multitudes
    0.77
    ,
    0.77
     ejac
    0.76
     эффективно
    0.75
     waged
    0.75
     свободно
    0.73
    ง
    0.73
     incroyable
    0.73
    Activations Density 0.000%

    No Known Activations