© 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. 5490
    Prev
    Next
    INDEX
    Explanations

    snippets of code and mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    code and filenames

    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
    ########.
    -0.80
     समीक्षाओं
    -0.68
     EconPapers
    -0.58
     OFDb
    -0.55
    ftagPool
    -0.53
    ThroughAttribute
    -0.52
    +#+
    -0.52
     ddelweddau
    -0.52
    脚注の使い方
    -0.51
    GOTREF
    -0.50
    POSITIVE LOGITS
     Planets
    0.47
     Municip
    0.46
    Escola
    0.45
    ordin
    0.44
     Prés
    0.44
     Espa
    0.44
    quia
    0.43
     Arquite
    0.43
     tartalomajánló
    0.43
     Propor
    0.42
    Activations Density 23.523%

    No Known Activations