© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219197
    Prev
    Next
    INDEX
    Explanations

    heart

    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_47_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
     пер
    0.42
     %=
    0.38
    男女
    0.38
    たたみ
    0.38
    %=
    0.38
    rapati
    0.36
     remedy
    0.36
    윕
    0.36
    沛
    0.35
    ನೇ
    0.35
    POSITIVE LOGITS
     lambs
    0.40
     ኦ
    0.40
     pull
    0.38
     jeste
    0.38
     bala
    0.38
     swan
    0.38
    angwa
    0.37
    SwitchCompat
    0.37
    Laurent
    0.37
     oxide
    0.37
    Activations Density 0.001%

    No Known Activations