© 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. 3453
    Prev
    Next
    INDEX
    Explanations

    code snippets and file paths within documentation or code-related text, particularly those related to web development or software configuration.

    oai_token-act-pair · gemini-2.0-flash

    code, programming

    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
    liana
    -0.45
     متعلقه
    -0.45
     including
    -0.45
    DataPropertyName
    -0.45
    addLast
    -0.45
     含
    -0.44
    ✭✭
    -0.44
    BASEPATH
    -0.43
    lian
    -0.42
     hin
    -0.42
    POSITIVE LOGITS
    twimg
    0.72
    ImageContext
    0.62
     arbete
    0.61
    šanai
    0.61
    الحياه
    0.59
    essions
    0.58
    ystems
    0.58
     său
    0.56
    ervice
    0.55
    клопе
    0.55
    Activations Density 16.172%

    No Known Activations