© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207058
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations/names

    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_46_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
     แล
    0.39
    辺
    0.37
     Pitts
    0.37
     Sonnen
    0.37
     Exotic
    0.37
     adulta
    0.36
     edilmesi
    0.36
    այի
    0.36
     দা
    0.35
     trì
    0.35
    POSITIVE LOGITS
     folate
    0.43
     MIL
    0.42
     pant
    0.40
     மாவட்டத்தில்
    0.39
    ೮
    0.38
     corals
    0.38
    MIL
    0.37
    𝘃
    0.37
    rements
    0.37
    cial
    0.36
    Activations Density 0.004%

    No Known Activations