© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49907
    Prev
    Next
    INDEX
    Explanations

    years old

    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_10_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
    জ
    0.45
     Algebras
    0.38
    لي
    0.38
    ম
    0.37
     Elementary
    0.37
     It
    0.37
     Eigent
    0.37
     Helicopter
    0.36
     Checking
    0.35
     Investigators
    0.35
    POSITIVE LOGITS
     commonplace
    0.39
     misappropri
    0.39
    ᱕
    0.38
    ی
    0.38
    N
    0.37
    5
    0.37
    ه
    0.37
    ता
    0.36
     کر
    0.35
     concili
    0.35
    Activations Density 0.000%

    No Known Activations