© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122052
    Prev
    Next
    INDEX
    Explanations

    explaining each step

    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_37_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
    哪
    0.39
     synthesize
    0.39
     lesquels
    0.37
    нка
    0.37
     WHEN
    0.37
    كمال
    0.36
    囟
    0.36
     उद
    0.36
    cein
    0.35
     cuales
    0.35
    POSITIVE LOGITS
     العديد
    0.39
     taxation
    0.38
     tradition
    0.38
     homosexuality
    0.37
     Lander
    0.37
     lymphoblastic
    0.37
    万
    0.36
    nextToken
    0.35
    representative
    0.35
     Cre
    0.35
    Activations Density 0.013%

    No Known Activations