© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46401
    Prev
    Next
    INDEX
    Explanations

    Stockholm syndrom

    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_13_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
     MEAN
    0.55
     dignity
    0.46
     konular
    0.46
     Eo
    0.46
     AREAS
    0.46
     организа
    0.45
    _)
    0.45
     Име
    0.44
     dignidad
    0.43
    ோர்
    0.43
    POSITIVE LOGITS
     Savaşı
    0.54
    可通过
    0.46
    自然
    0.46
    atural
    0.46
     führte
    0.45
    سكرية
    0.44
    শ্বরের
    0.43
                                 
    0.43
    giants
    0.43
    巨人
    0.43
    Activations Density 0.000%

    No Known Activations