© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79997
    Prev
    Next
    INDEX
    Explanations

    on the ... graph/map/plane

    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_31_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
    ‌های
    0.40
    omination
    0.38
     marked
    0.38
    composite
    0.36
    组成的
    0.36
    মেয়
    0.35
     ترکیب
    0.35
    倹
    0.35
     বাহ
    0.34
    রাধ
    0.34
    POSITIVE LOGITS
    rumah
    0.46
     اسٹی
    0.45
     tav
    0.43
     overturned
    0.39
     kormány
    0.39
     specialized
    0.38
     pegawai
    0.38
     langsung
    0.37
     KK
    0.37
     swung
    0.37
    Activations Density 0.003%

    No Known Activations