© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9692
    Prev
    Next
    INDEX
    Explanations

    phrases involving permissions, risks, and conditions

    oai_token-act-pair · gemini-2.0-flash

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     reality
    -0.59
    aarrggbb
    -0.59
     старости
    -0.51
     resourceCulture
    -0.50
    ClientSize
    -0.49
     realities
    -0.48
     nonUne
    -0.48
     dale
    -0.47
     Oscars
    -0.47
     unknownFields
    -0.47
    POSITIVE LOGITS
     idées
    0.61
     méta
    0.59
     fermés
    0.59
     dépens
    0.59
     venons
    0.58
     acrylique
    0.57
     démocr
    0.57
     découver
    0.56
     réfugiés
    0.56
     détru
    0.56
    Activations Density 1.174%

    No Known Activations