© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195515
    Prev
    Next
    INDEX
    Explanations

    say "ase"

    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_50_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
    ming
    0.42
    앱
    0.41
    avila
    0.41
    ផ្ល
    0.40
    пер
    0.37
     mannit
    0.37
     বিশ্লেষণের
    0.37
    殷
    0.37
    বিহার
    0.37
    ynu
    0.36
    POSITIVE LOGITS
    hose
    0.58
     hose
    0.52
    Ease
    0.52
     ease
    0.50
    ease
    0.47
    তেন
    0.46
     mous
    0.44
     Hose
    0.43
    olese
    0.41
     eases
    0.41
    Activations Density 0.001%

    No Known Activations