© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179118
    Prev
    Next
    INDEX
    Explanations

    bullying

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Kangaroo
    0.46
    ulc
    0.45
     camb
    0.44
    camb
    0.44
     Camb
    0.42
    iorari
    0.40
    𝖘
    0.40
    Camb
    0.38
     kangaroo
    0.37
     chameleon
    0.37
    POSITIVE LOGITS
     mo
    0.47
     pier
    0.43
     புர
    0.40
    EF
    0.38
    Pier
    0.38
    衚
    0.38
    ឧបករណ៍
    0.38
     nig
    0.38
    盹
    0.38
    unfinished
    0.38
    Activations Density 0.006%

    No Known Activations