© 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. 619
    Prev
    Next
    INDEX
    Explanations

    documentation (like tutorials or device overviews) of computer or electronic components, especially connection/wiring-related

    oai_token-act-pair · gemini-2.0-flash

    connecting electronic components

    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
    alyptus
    -0.52
    Pfalz
    -0.48
    politan
    -0.47
     незавершена
    -0.45
     project
    -0.44
     crédit
    -0.44
     podjela
    -0.44
     kaarangay
    -0.43
    éraux
    -0.43
    ItemGroup
    -0.43
    POSITIVE LOGITS
    PhysRevD
    0.75
     MainAxisSize
    0.66
    didSet
    0.65
     light
    0.59
    ArgsConstructor
    0.59
     typelib
    0.58
    NullException
    0.56
    Portail
    0.54
     resourceCulture
    0.54
     Reverso
    0.54
    Activations Density 5.687%

    No Known Activations