© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248232
    Prev
    Next
    INDEX
    Explanations

    launch

    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_56_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
     interpreted
    0.47
     occupied
    0.46
     present
    0.46
     passado
    0.43
     concluded
    0.41
     consumed
    0.39
     ocup
    0.39
    蝦
    0.39
     resolved
    0.39
     involved
    0.39
    POSITIVE LOGITS
     Launches
    0.69
     launches
    0.64
    launch
    0.62
    Launch
    0.62
     launch
    0.55
    LAUNCH
    0.55
     lanç
    0.53
     Launch
    0.52
     लॉन्च
    0.52
    Launcher
    0.52
    Activations Density 0.001%

    No Known Activations