© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199283
    Prev
    Next
    INDEX
    Explanations

    predators and attacks

    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_12_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
     UFC
    0.54
     θέση
    0.53
    ছে
    0.52
     பெண்
    0.51
    ்த்த
    0.49
    pecific
    0.49
    夆
    0.48
    豹
    0.47
     গুরুত্বপূর্ণ
    0.47
    istema
    0.47
    POSITIVE LOGITS
     Pendidikan
    0.55
    hidrat
    0.54
     ක්ර
    0.54
    palindrome
    0.53
     szín
    0.52
    ?".
    0.52
     Saccharomyces
    0.51
    train
    0.50
     ಹೇಳ
    0.50
    string
    0.49
    Activations Density 0.032%

    No Known Activations