© 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. 14384
    Prev
    Next
    INDEX
    Explanations

    fragments of some nonsensical religious or violent text possibly machine-generated

    oai_token-act-pair · gemini-2.0-flash

    japanese media

    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
     surla
    -0.68
    ">//
    -0.68
     мәкал
    -0.67
    Tembelea
    -0.66
     tqdm
    -0.66
     <=",
    -0.65
    Hauptartikel
    -0.60
    thâu
    -0.58
     itſelf
    -0.58
    umerable
    -0.58
    POSITIVE LOGITS
    djangoproject
    0.47
     tocar
    0.44
    Boot
    0.44
    fxml
    0.44
    WebControls
    0.42
    InteropServices
    0.41
    inos
    0.41
    ngrx
    0.41
     kræ
    0.41
     vors
    0.41
    Activations Density 2.441%

    No Known Activations