© 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. 4482
    Prev
    Next
    INDEX
    Explanations

    text extracted from sourcecode or configuration files

    oai_token-act-pair · gemini-2.0-flash

    SMS account verification

    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
     Мексичка
    -1.08
    resave
    -1.05
    Personensuche
    -1.01
    GEBURTSDATUM
    -0.98
     typelib
    -0.96
     ainfi
    -0.96
     Theſe
    -0.94
     незавершена
    -0.93
    )];
    -0.93
     Shakspeare
    -0.93
    POSITIVE LOGITS
     the
    0.80
    -
    0.79
     a
    0.76
     on
    0.75
     one
    0.69
     in
    0.68
     an
    0.66
     are
    0.66
     use
    0.63
     important
    0.63
    Activations Density 0.268%

    No Known Activations