© 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-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14496
    Prev
    Next
    INDEX
    Explanations

    references to death, violence, and crime

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms and error messages

    np_token-act-pair-logits · gpt-4o-mini

    murder

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     оно
    -0.69
    Its
    -0.61
    它
    -0.59
     Its
    -0.58
     которое
    -0.58
    It
    -0.56
     of
    -0.54
    dis
    -0.52
    its
    -0.52
     яке
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    1.27
     '\\;'
    0.92
     calendriers
    0.91
     EconPapers
    0.90
    MemoryWarning
    0.90
    GEBURTSDATUM
    0.83
    FormTagHelper
    0.83
    ivably
    0.79
    ">—
    0.78
     للاسماء
    0.78
    Activations Density 11.686%

    No Known Activations