© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29417
    Prev
    Next
    INDEX
    Explanations

    stealing or theft

    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_10_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
    ir
    0.88
    ра
    0.86
    ة
    0.81
    ર
    0.81
    ut
    0.77
    ot
    0.71
    ar
    0.70
    ार
    0.69
    なった
    0.69
    il
    0.68
    POSITIVE LOGITS
     stealing
    0.88
     steals
    0.87
     steal
    0.84
     theft
    0.82
     thefts
    0.81
     stolen
    0.78
     চুরি
    0.77
    훔
    0.77
     stole
    0.76
     çal
    0.70
    Activations Density 0.027%

    No Known Activations