© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10424
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to mathematical and logical reasoning, especially 'show' and 'using'.

    oai_token-act-pair · gemini-2.0-flash

    code/technical documentation

    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
    ########.
    -0.59
     actionMode
    -0.59
    SBATCH
    -0.57
     ExecuteAsync
    -0.57
    uttgart
    -0.54
     StatefulWidget
    -0.54
     oprot
    -0.52
     Allociné
    -0.52
    ogues
    -0.52
    thren
    -0.51
    POSITIVE LOGITS
    UserScript
    0.52
     word
    0.52
    LookAnd
    0.50
    ChildIndex
    0.48
     fær
    0.48
     Infórmanos
    0.46
     palabra
    0.45
     uppgifter
    0.45
     ideje
    0.44
     prieš
    0.44
    Activations Density 9.188%

    No Known Activations