© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15445
    Prev
    Next
    INDEX
    Explanations

    mentions of various motivations for criminal acts

    oai_token-act-pair · gemini-2.0-flash

    crime and murder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.95
     betweenstory
    -0.85
     snippetHide
    -0.82
    fjspx
    -0.80
    AutoresizingMask
    -0.77
     otomatig
    -0.77
     defaultstate
    -0.77
    IBOutlet
    -0.76
    ConstraintMaker
    -0.75
    CppCodeGen
    -0.73
    POSITIVE LOGITS
     posibil
    0.42
     ++)
    0.42
     governador
    0.40
     financières
    0.39
    ragona
    0.38
    υγ
    0.38
    ванович
    0.37
     deur
    0.36
     влади
    0.35
    null
    0.35
    Activations Density 0.556%

    No Known Activations