© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260333
    Prev
    Next
    INDEX
    Explanations

    heterosexuals and straight people

    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_22_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
    GALAD
    0.45
     කරයි
    0.42
     LABEL
    0.42
     ছবির
    0.41
    claves
    0.41
     UserName
    0.41
    RationalValue
    0.41
     숫
    0.40
     WorldCat
    0.40
     Wikipédia
    0.40
    POSITIVE LOGITS
    ild
    0.45
     natural
    0.39
     Tillman
    0.38
     land
    0.38
     natuur
    0.38
    -
    0.37
     agricult
    0.37
     agricultural
    0.37
    ­
    0.37
     naturally
    0.37
    Activations Density 0.002%

    No Known Activations