© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213842
    Prev
    Next
    INDEX
    Explanations

    captivity and zoos

    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_43_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
     atra
    0.41
     BK
    0.39
    BK
    0.38
    Animal
    0.38
     mk
    0.37
    Deb
    0.36
     동물
    0.35
    況
    0.35
    㓞
    0.35
    bk
    0.35
    POSITIVE LOGITS
     Disneyland
    0.46
     मरने
    0.41
    трибу
    0.41
    दिल्ली
    0.40
    اطع
    0.40
    尽可能
    0.39
    -{\
    0.39
    𒌉
    0.39
     अभिव्यक्ति
    0.39
    microseconds
    0.39
    Activations Density 0.001%

    No Known Activations