© 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. 4413
    Prev
    Next
    INDEX
    Explanations

    explanations of online security vulnerabilities

    oai_token-act-pair · gemini-2.0-flash

    Accessing, stealing

    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
    RenderAtEndOf
    -0.91
     myſelf
    -0.89
     resourceCulture
    -0.87
     ſeveral
    -0.86
     estekak
    -0.86
    Personensuche
    -0.85
    ConstraintMaker
    -0.85
     itſelf
    -0.82
     Theſe
    -0.82
    MigrationBuilder
    -0.81
    POSITIVE LOGITS
    Accessing
    0.51
     accessing
    0.41
     log
    0.40
    Tapped
    0.40
    burgs
    0.39
     mod
    0.38
     steal
    0.37
     accéder
    0.36
    ท์
    0.36
    ია
    0.35
    Activations Density 7.066%

    No Known Activations