© 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. 218114
    Prev
    Next
    INDEX
    Explanations

    places and environments

    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
     partners
    0.38
     forse
    0.38
     consort
    0.37
     zhōng
    0.36
     setengah
    0.36
     allege
    0.35
     partner
    0.35
     進
    0.35
     proclaims
    0.35
     subst
    0.35
    POSITIVE LOGITS
     Shir
    0.47
    Shir
    0.46
     Shiraz
    0.42
     شیع
    0.41
    morph
    0.39
     iran
    0.39
    Iran
    0.39
     Shia
    0.39
    蘸
    0.38
     Piotr
    0.37
    Activations Density 0.001%

    No Known Activations