© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18313
    Prev
    Next
    INDEX
    Explanations

    account compromised, experienced 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_34_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
    疏
    0.35
    нке
    0.35
     aging
    0.34
    丶
    0.34
     behavioral
    0.33
     Kong
    0.33
    azin
    0.32
    जु
    0.32
     Julie
    0.32
     Jasmine
    0.31
    POSITIVE LOGITS
    都被
    0.65
     kidnapped
    0.64
     bị
    0.61
     attacked
    0.61
     abducted
    0.61
    被
    0.60
     kidnap
    0.59
     kidnapping
    0.58
     harassed
    0.58
    会被
    0.58
    Activations Density 0.171%

    No Known Activations