© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116374
    Prev
    Next
    INDEX
    Explanations

    deductive reasoning

    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_27_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
     Qxd
    0.37
    ديد
    0.37
     painkillers
    0.37
     fios
    0.36
    鹕
    0.35
    वट
    0.35
     थरूर
    0.35
     stressing
    0.35
     Treated
    0.34
    峭
    0.34
    POSITIVE LOGITS
     부터
    0.41
    陆续
    0.41
    áp
    0.39
     를
    0.37
    iseite
    0.37
    lauf
    0.36
    punkt
    0.36
    )}}{\
    0.36
    命
    0.35
     laterally
    0.35
    Activations Density 0.000%

    No Known Activations