© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4162
    Prev
    Next
    INDEX
    Explanations

    memorizing, perpetuating, destabilizing, manipulating

    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_39_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
    🫦
    0.44
    ingly
    0.42
    िंग्स
    0.41
    ől
    0.39
    oshin
    0.38
    釗
    0.38
    assurer
    0.38
     जेब
    0.38
    Resultado
    0.38
     querer
    0.37
    POSITIVE LOGITS
    ating
    0.45
    izing
    0.45
    化
    0.44
    ization
    0.42
    isation
    0.41
    ATING
    0.39
    নমেন্ট
    0.38
    ize
    0.37
     erc
    0.36
    gum
    0.36
    Activations Density 0.273%

    No Known Activations