© 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. 14882
    Prev
    Next
    INDEX
    Explanations

    capitalized words, abbreviations, and words following numbers

    oai_token-act-pair · gemini-2.0-flash

    Predictions of the future

    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
    ](#
    -0.56
    ()]
    -0.54
    });*/
    -0.52
    >-->
    -0.51
    wachsene
    -0.51
     vérit
    -0.50
    =*/
    -0.50
     démocratie
    -0.49
    »։
    -0.49
    клопе
    -0.48
    POSITIVE LOGITS
     Point
    0.44
     Plate
    0.43
     Circle
    0.42
     Moment
    0.40
     Group
    0.40
    providedIn
    0.39
     Unit
    0.39
     Loop
    0.39
     Count
    0.38
     House
    0.38
    Activations Density 3.258%

    No Known Activations