© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48421
    Prev
    Next
    INDEX
    Explanations

    blog post article

    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_31_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
     נק
    0.33
     공간
    0.32
     పే
    0.31
     Twins
    0.31
    설
    0.30
    ActiveClass
    0.29
     βιβ
    0.29
     활
    0.29
     διαφορε
    0.29
    志
    0.29
    POSITIVE LOGITS
    colorize
    0.29
     બ્
    0.29
     digesting
    0.29
    ackets
    0.29
    ိုင်း
    0.29
     haciendo
    0.29
     procédures
    0.29
    oub
    0.28
     Blogger
    0.28
    ako
    0.28
    Activations Density 0.004%

    No Known Activations