© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2166
    Prev
    Next
    INDEX
    Explanations

    text describing pinkeye

    oai_token-act-pair · gemini-2.0-flash

    French words related to symptoms and conditions

    np_token-act-pair-logits · gpt-4o-mini

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    "]();
    -0.56
    جغرافيا
    -0.56
    '},
    -0.56
    RouterModule
    -0.53
    esten
    -0.53
    !';
    -0.52
    Portale
    -0.52
    PositiveButton
    -0.51
    phosa
    -0.50
    ++];
    -0.50
    POSITIVE LOGITS
     blessés
    0.68
     bénévoles
    0.68
     réfugi
    0.64
     preuves
    0.60
     fidélité
    0.60
     varandra
    0.59
     cérami
    0.56
     doppia
    0.55
     amitié
    0.55
     supérieurs
    0.54
    Activations Density 6.648%

    No Known Activations