© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14607
    Prev
    Next
    INDEX
    Explanations

    a mix of general language used in several contexts: data analysis, business scaling, user participation and time

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ########.
    -0.79
    +#+#
    -0.77
     Efq
    -0.72
    ModelAdmin
    -0.72
     defaultstate
    -0.71
    />";
    -0.70
    ."));
    -0.70
    )");
    -0.69
    NameInMap
    -0.69
    Personendaten
    -0.69
    POSITIVE LOGITS
    my
    0.46
    uch
    0.44
    My
    0.40
    قایناق‌لار
    0.40
     dating
    0.38
     my
    0.38
    Ä
    0.38
     tu
    0.38
    oriques
    0.38
     Aso
    0.37
    Activations Density 0.466%

    No Known Activations