© 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. 220344
    Prev
    Next
    INDEX
    Explanations

    academic record and degrees

    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
    垷
    0.42
     schooling
    0.42
     saddles
    0.41
     girls
    0.39
    SCHOOL
    0.39
     लड़कियों
    0.37
    CharCode
    0.37
    蒙古
    0.37
    䡋
    0.37
     school
    0.36
    POSITIVE LOGITS
     Solving
    0.42
     Detective
    0.41
     solve
    0.39
    Detective
    0.39
    odot
    0.39
     Solve
    0.39
     sieci
    0.38
     thái
    0.38
     pront
    0.38
     intellectual
    0.37
    Activations Density 0.000%

    No Known Activations