© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214894
    Prev
    Next
    INDEX
    Explanations

    before

    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
     बिस्तर
    0.41
    噛
    0.40
    igem
    0.38
    โทร
    0.38
     посте
    0.38
     Bed
    0.37
     සි
    0.37
     বুঝিতে
    0.37
     বিছ
    0.37
    夜
    0.37
    POSITIVE LOGITS
     Reb
    0.38
     lineHeight
    0.38
     Dy
    0.38
     Hoffmann
    0.37
     back
    0.37
     reb
    0.37
    aired
    0.37
     av
    0.36
     Pyr
    0.36
     luft
    0.36
    Activations Density 0.001%

    No Known Activations