© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13456
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of electronic devices such as tablets and TVs

    oai_token-act-pair · gemini-2.0-flash

    technical device descriptions

    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
    AccessorTable
    -0.63
    LEncoder
    -0.63
    tagHelperRunner
    -0.62
    jamientos
    -0.58
    StructEnd
    -0.57
     onCreateView
    -0.57
    @[+][
    -0.57
    ineno
    -0.57
    IUrlHelper
    -0.56
    Cyfeiriadau
    -0.55
    POSITIVE LOGITS
     loch
    0.52
     članak
    0.52
    Produzione
    0.49
     Drivers
    0.48
    CAD
    0.48
    Kart
    0.47
    kozás
    0.47
    apist
    0.47
     Poor
    0.46
    DRM
    0.46
    Activations Density 15.098%

    No Known Activations