© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11185
    Prev
    Next
    INDEX
    Explanations

    words describing and related to crimes

    oai_token-act-pair · gemini-2.0-flash

    crime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     crime
    -2.20
     Crime
    -1.91
    crime
    -1.88
    Crime
    -1.74
     CRIME
    -1.72
     crimes
    -1.38
    crimes
    -1.26
     Crimes
    -1.20
     crimen
    -1.06
    犯罪
    -1.01
    POSITIVE LOGITS
    <bos>
    0.69
    ⓧ
    0.69
    MessageTagHelper
    0.68
    SourceChecksum
    0.66
    apunov
    0.63
    GEBURTSDATUM
    0.62
     disambiguazione
    0.60
    AutoField
    0.60
    ValueStyle
    0.59
    tadiene
    0.57
    Activations Density 1.032%

    No Known Activations