© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89302
    Prev
    Next
    INDEX
    Explanations

    lay of the land

    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_11_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
    Brains
    0.59
    irar
    0.56
     Шве
    0.56
    Doctrine
    0.55
     आढळ
    0.55
    am
    0.55
    ม
    0.55
     Mosk
    0.54
    ويم
    0.54
    𝚖
    0.54
    POSITIVE LOGITS
     extens
    0.55
     hall
    0.55
     features
    0.53
     pantalla
    0.52
    フロ
    0.51
     victimization
    0.51
     jo
    0.50
     hallway
    0.50
     comparability
    0.49
     gradu
    0.49
    Activations Density 0.000%

    No Known Activations