© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195007
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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_27_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
    Дата
    0.39
    adin
    0.38
     Summary
    0.36
     एसएससी
    0.36
    MUST
    0.35
     Successfully
    0.34
     एक्ट्रेसेस
    0.34
    ⬅
    0.34
    情況
    0.33
     Presumably
    0.33
    POSITIVE LOGITS
     muchos
    0.47
     storytelling
    0.41
     frutto
    0.41
     semangat
    0.40
     Baal
    0.39
     pride
    0.39
     orgullo
    0.39
     dedicada
    0.38
     nuestra
    0.38
     cặp
    0.38
    Activations Density 0.001%

    No Known Activations