© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10804
    Prev
    Next
    INDEX
    Explanations

    technical language used in scientific and mathematical writing, especially related to data and medicine.

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Normal
    -3.06
     normal
    -3.05
    Normal
    -3.03
    normal
    -2.84
     NORMAL
    -2.75
    NORMAL
    -2.47
     normale
    -2.42
     normales
    -2.39
     normality
    -2.27
    norm
    -2.25
    POSITIVE LOGITS
     متعلقه
    0.69
     GenerationType
    0.69
    ReusableCell
    0.63
    enumi
    0.62
    ScopeManager
    0.62
     AppDelegate
    0.61
     فريبيس
    0.60
    ğından
    0.56
    gonic
    0.56
    CreateModel
    0.56
    Activations Density 3.832%

    No Known Activations