© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242843
    Prev
    Next
    INDEX
    Explanations

    year followed by a number

    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_40_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
    பு
    0.38
     पार्टियों
    0.38
    琴
    0.38
    istán
    0.38
     hospitals
    0.36
    ைக்கு
    0.36
    Creator
    0.35
    婊
    0.35
     پە
    0.34
    ิ้น
    0.34
    POSITIVE LOGITS
    ulação
    0.43
     desf
    0.42
     entidade
    0.41
    nent
    0.39
     esquina
    0.39
     destacado
    0.39
    tion
    0.38
    tional
    0.37
     duduk
    0.37
     اربعه
    0.37
    Activations Density 0.000%

    No Known Activations