© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12910
    Prev
    Next
    INDEX
    Explanations

    references to national organizations, roles, or departments

    oai_token-act-pair · gemini-2.0-flash

    National

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Efq
    -1.15
     Theſe
    -1.13
     itſelf
    -1.12
     Monfieur
    -1.12
     myſelf
    -1.11
     ―――――
    -1.06
     ſeveral
    -1.06
     uſed
    -1.02
     raiſ
    -1.02
     whoſe
    -1.02
    POSITIVE LOGITS
     la
    0.56
     g
    0.54
     y
    0.48
     el
    0.48
     r
    0.47
     pa
    0.47
     G
    0.46
     is
    0.46
     in
    0.45
    ↵
    0.45
    Activations Density 1.803%

    No Known Activations