© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216440
    Prev
    Next
    INDEX
    Explanations

    harmful stereotypes

    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_31_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
     unexpectedly
    0.41
    ో
    0.37
     Dem
    0.36
     serv
    0.34
     demolition
    0.34
     bölüm
    0.34
     syndrome
    0.34
     motivating
    0.34
     Bern
    0.33
     torno
    0.33
    POSITIVE LOGITS
    ⱨ
    0.41
    此处
    0.40
    presumably
    0.39
    copies
    0.38
    lores
    0.38
    和其他
    0.37
    Ia
    0.37
    闶
    0.36
    regulate
    0.36
    eseed
    0.36
    Activations Density 0.020%

    No Known Activations