© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207057
    Prev
    Next
    INDEX
    Explanations

    cannons and guns

    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_56_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
     fire
    0.59
     Fire
    0.59
    Fire
    0.58
     FIRE
    0.54
    fire
    0.49
    火
    0.49
     آتش
    0.44
     फायर
    0.44
     gun
    0.43
    FIRE
    0.43
    POSITIVE LOGITS
     repeating
    0.50
     chests
    0.46
     staffs
    0.44
     répét
    0.43
     Repe
    0.43
     funcionários
    0.43
    菱
    0.42
     repeat
    0.41
    Repeating
    0.41
     employés
    0.41
    Activations Density 0.001%

    No Known Activations