© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216653
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    ირო
    0.44
    tank
    0.42
    sqlUpdate
    0.37
     ホ
    0.36
    Tank
    0.36
    PosX
    0.36
    тные
    0.35
    <unused77>
    0.35
    শ্রে
    0.35
     sinon
    0.35
    POSITIVE LOGITS
     moving
    0.42
     mum
    0.41
     Lied
    0.40
     ट्रैफिक
    0.39
    mum
    0.38
     literate
    0.38
     Mum
    0.37
    ведений
    0.37
    Mum
    0.37
    ve
    0.37
    Activations Density 0.001%

    No Known Activations