© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12880
    Prev
    Next
    INDEX
    Explanations

    the word "policy"

    oai_token-act-pair · gemini-2.0-flash

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.01
     initComponents
    -0.84
    SequentialGroup
    -0.84
    +#+#
    -0.74
     snippetHide
    -0.74
    Hochspringen
    -0.73
     nakalista
    -0.73
    /*
    -0.70
     مشارکت‌کنندگان
    -0.69
     дописавши
    -0.68
    POSITIVE LOGITS
     dangereux
    0.60
    same
    0.59
     same
    0.52
    audiovisuel
    0.50
    joni
    0.49
     reconnu
    0.49
    Same
    0.48
     présidenti
    0.48
     Same
    0.47
     essentiellement
    0.46
    Activations Density 0.309%

    No Known Activations