© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with crime

    oai_token-act-pair · gemini-2.0-flash

    terms related to criminal behavior

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

    childhood risk behaviors

    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
    脚注の使い方
    -0.73
    WaitGroup
    -0.66
    RefNanny
    -0.63
     onCancelled
    -0.61
    rungsseite
    -0.60
    Hentet
    -0.58
     religieux
    -0.57
     Superhosts
    -0.57
    tagext
    -0.57
    )))),
    -0.56
    POSITIVE LOGITS
    やん
    0.49
     rejet
    0.46
    ヤン
    0.46
     bullies
    0.44
    delin
    0.43
    radora
    0.43
    wana
    0.43
     newOwner
    0.42
    viaf
    0.42
     delinquent
    0.42
    Activations Density 2.338%

    No Known Activations