© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169145
    Prev
    Next
    INDEX
    Explanations

    updating or donating

    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
    ove
    0.42
    樋
    0.38
     vuelto
    0.38
     pretzel
    0.38
    iyim
    0.38
     overs
    0.37
    üğünüz
    0.36
    vius
    0.36
    เขต
    0.35
    塁
    0.35
    POSITIVE LOGITS
    updating
    0.43
     updating
    0.42
    donate
    0.39
     ajoute
    0.38
    CopyWith
    0.37
    க்கொள்
    0.37
     Updating
    0.37
    <0x0F>
    0.37
    కోవ
    0.36
     donating
    0.36
    Activations Density 0.000%

    No Known Activations