© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11585
    Prev
    Next
    INDEX
    Explanations

    hostage and prisoner related terms

    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_40_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
     Devon
    0.38
    cookieParser
    0.37
     шокола
    0.37
     wah
    0.37
    ванию
    0.36
    Tema
    0.36
    研
    0.35
    𝒜
    0.35
     Textured
    0.35
     File
    0.35
    POSITIVE LOGITS
     prisoner
    1.86
     prisoners
    1.68
     hostage
    1.63
    prisoner
    1.62
     Prisoner
    1.59
     Prisoners
    1.57
     captive
    1.55
    prisoners
    1.49
     hostages
    1.47
     captives
    1.38
    Activations Density 0.039%

    No Known Activations