© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53572
    Prev
    Next
    INDEX
    Explanations

    escape

    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_55_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
    沚
    0.37
     স্থ
    0.37
    哿
    0.37
    優
    0.36
    住
    0.35
     تای
    0.35
     WS
    0.35
     डिटेल्स
    0.34
    不住
    0.34
    anse
    0.34
    POSITIVE LOGITS
     escape
    3.25
     escapes
    3.06
     escaped
    3.05
    escape
    2.95
     Escape
    2.95
    Escape
    2.86
     escaping
    2.84
    escap
    2.59
    逃
    2.59
     escap
    2.36
    Activations Density 0.031%

    No Known Activations