© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37768
    Prev
    Next
    INDEX
    Explanations

    quickly leads to escalation

    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_11_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
     ως
    0.58
    нома
    0.57
    ug
    0.56
    imit
    0.54
    জিত
    0.54
    "};
    0.52
    är
    0.52
     agarr
    0.52
    ᧐
    0.51
    rawberry
    0.51
    POSITIVE LOGITS
    대
    0.71
     strany
    0.57
    depression
    0.57
    डे
    0.57
     KX
    0.55
    leben
    0.55
    lerden
    0.55
    الن
    0.55
    labs
    0.54
    পুণ
    0.54
    Activations Density 0.005%

    No Known Activations