© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    programming code

    oai_token-act-pair · gemini-2.0-flash

    +

    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
    ágot
    -0.61
    لیس
    -0.60
     Shakspeare
    -0.59
    Carcinogenicity
    -0.59
    orsese
    -0.58
     Lippincott
    -0.58
     chaste
    -0.57
     vPvB
    -0.57
    Ecotoxicity
    -0.55
     Litchfield
    -0.55
    POSITIVE LOGITS
    tagHelperRunner
    0.61
    onthe
    0.57
     On
    0.57
     EdgeInsets
    0.53
    SharedCtor
    0.53
    ệu
    0.53
     endforeach
    0.52
     on
    0.52
     '\\;'
    0.51
    ंदीखरीदारी
    0.50
    Activations Density 15.316%

    No Known Activations