© 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. 179154
    Prev
    Next
    INDEX
    Explanations

    word parts

    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
    itel
    0.78
    iteľ
    0.69
    ITE
    0.67
    itele
    0.66
    itely
    0.65
    ite
    0.53
    iteli
    0.52
    <0x8A>
    0.51
    itelja
    0.51
    вите
    0.51
    POSITIVE LOGITS
    排除
    0.40
    zza
    0.38
     dragged
    0.38
     phân
    0.37
    వే
    0.37
    permissionid
    0.35
    ٖ
    0.35
     propagated
    0.35
    Nik
    0.34
     Faun
    0.34
    Activations Density 0.001%

    No Known Activations