© 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. 216286
    Prev
    Next
    INDEX
    Explanations

    python code

    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
     singularities
    0.44
     singularity
    0.40
    🤨
    0.39
     ప్రతి
    0.39
     সাং
    0.39
     SINGH
    0.38
     FY
    0.37
     wavefront
    0.37
    😗
    0.37
    KEL
    0.36
    POSITIVE LOGITS
     conteú
    0.42
     dopln
    0.40
     endeavors
    0.37
     alongside
    0.36
    hanahu
    0.36
     endeavor
    0.35
    Работа
    0.35
     leben
    0.35
    जीव
    0.35
    anyan
    0.35
    Activations Density 0.000%

    No Known Activations