© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242278
    Prev
    Next
    INDEX
    Explanations

    spring data jpa

    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_40_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
    ခြေ
    0.39
    rectomy
    0.39
     penta
    0.38
    ótica
    0.38
    鯨
    0.38
     pohon
    0.38
    kangaroo
    0.38
    posable
    0.37
    ঞ্চলের
    0.37
     ғ
    0.37
    POSITIVE LOGITS
    是谁
    0.38
     marked
    0.38
    Creator
    0.38
     creator
    0.38
    icier
    0.37
     Creator
    0.37
    催
    0.36
     sulfur
    0.35
    Mold
    0.35
     catalogues
    0.34
    Activations Density 0.000%

    No Known Activations