© 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. 12461
    Prev
    Next
    INDEX
    Explanations

    text relating to study design and statistical analysis

    oai_token-act-pair · gemini-2.0-flash

    Physical activity studies

    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
     PA
    -1.77
     Pa
    -1.70
    Pa
    -1.63
     pa
    -1.54
    PA
    -1.46
     PAL
    -1.45
    PAL
    -1.39
     Pal
    -1.38
    Pal
    -1.38
     Pennsylvania
    -1.37
    POSITIVE LOGITS
     Infórmanos
    0.57
    OGND
    0.56
    principalTable
    0.51
     Савезне
    0.45
    localScale
    0.44
     danza
    0.44
    évaluateur
    0.43
    umą
    0.43
     Roskov
    0.42
     مرئيه
    0.41
    Activations Density 1.569%

    No Known Activations