© 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. 5135
    Prev
    Next
    INDEX
    Explanations

    web development code syntax, including HTML, CSS, and Javascript

    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
     mergeFrom
    -0.72
     متعلقه
    -0.69
    writeField
    -0.66
    StoryboardSegue
    -0.65
     виправивши
    -0.63
     विश्वसनीयता
    -0.61
    devamını
    -0.60
    RenderAtEndOf
    -0.59
     يتيمه
    -0.58
    ^(@)
    -0.58
    POSITIVE LOGITS
    ddots
    0.48
     sqlSession
    0.47
    Dichlorobenzene
    0.45
    OTER
    0.45
    XmlAccessType
    0.45
     Carbide
    0.44
    ffekt
    0.44
    dubbo
    0.44
    PickerController
    0.43
    instancetype
    0.43
    Activations Density 4.522%

    No Known Activations