© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16087
    Prev
    Next
    INDEX
    Explanations

    instances of the word "risk" along with closely related terms

    oai_token-act-pair · gemini-2.0-flash

    risk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     MainAxisSize
    -0.85
     risk
    -0.72
     Audiodateien
    -0.67
     RISK
    -0.65
     Risk
    -0.64
    Risk
    -0.63
    risk
    -0.62
     незавершена
    -0.60
    OGND
    -0.58
     risks
    -0.56
    POSITIVE LOGITS
    zule
    0.56
    ific
    0.53
    Rüyada
    0.51
    QMetaType
    0.50
    principalTable
    0.50
    ULTY
    0.49
    htb
    0.47
     adap
    0.47
    صاد
    0.47
    poons
    0.46
    Activations Density 2.664%

    No Known Activations