© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66655
    Prev
    Next
    INDEX
    Explanations

    lost or stolen

    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_41_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
    蜓
    0.45
    らく
    0.38
    MakeRect
    0.37
    Room
    0.37
    排除
    0.36
    튬
    0.36
    coverageStat
    0.35
    Lever
    0.34
    RequestParam
    0.34
     র‌
    0.33
    POSITIVE LOGITS
     stolen
    2.83
     steal
    2.83
     stole
    2.80
     stealing
    2.77
     steals
    2.58
     theft
    2.41
    steal
    2.28
    盗
    2.22
     thefts
    2.19
     Theft
    2.14
    Activations Density 0.009%

    No Known Activations