© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104546
    Prev
    Next
    INDEX
    Explanations

    killer night dead

    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_44_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
    garan
    0.43
     Preferred
    0.42
    सीआर
    0.40
    getinfo
    0.40
    ലോക
    0.39
    Preferred
    0.39
     जरूरत
    0.38
    🌺
    0.38
    راتكم
    0.38
    ग़
    0.37
    POSITIVE LOGITS
     killer
    0.52
    night
    0.50
    Night
    0.46
     Killer
    0.46
     March
    0.46
     Night
    0.44
     night
    0.44
    Killer
    0.43
     dead
    0.43
     Revenge
    0.42
    Activations Density 0.002%

    No Known Activations