© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48697
    Prev
    Next
    INDEX
    Explanations

    description

    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_55_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
     calibrate
    0.46
     pouvoirs
    0.45
    atched
    0.42
     releasing
    0.41
    Config
    0.39
    睦
    0.39
    Stef
    0.38
     contains
    0.38
     perform
    0.38
     processes
    0.38
    POSITIVE LOGITS
    सरण
    0.43
    :>
    0.42
     ocult
    0.38
    }}}{
    0.36
    ='/
    0.35
     रिजर्व
    0.35
     प्योर
    0.35
    ='',
    0.35
    appendTo
    0.34
    дон
    0.34
    Activations Density 0.004%

    No Known Activations