© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10304
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words related to trends, scales, and changes

    oai_token-act-pair · gemini-2.0-flash

    Reaching a limit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Personensuche
    -0.91
    TagMode
    -0.87
    tagHelperRunner
    -0.81
    ArgsConstructor
    -0.78
    AddTagHelper
    -0.77
    IntoConstraints
    -0.76
     мәкал
    -0.75
    Personendaten
    -0.75
    ChildScrollView
    -0.75
    ंदीखरीदारी
    -0.75
    POSITIVE LOGITS
    IFORN
    0.43
    omenta
    0.43
    propylene
    0.40
    diğ
    0.40
    FunctionName
    0.39
     unica
    0.38
    UMEN
    0.38
    ظر
    0.37
    Utils
    0.37
     M
    0.37
    Activations Density 3.501%

    No Known Activations