© 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. 15524
    Prev
    Next
    INDEX
    Explanations

    parts of words from various languages mixed together

    oai_token-act-pair · gemini-2.0-flash

    Scientific publications

    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
    Portale
    -0.63
    PhysRevD
    -0.58
    transQ
    -0.56
    ]--;
    -0.55
    rungsseite
    -0.54
    tonode
    -0.53
    StoreMessageInfo
    -0.53
    ViewInit
    -0.53
     isNameExpr
    -0.52
    __((
    -0.52
    POSITIVE LOGITS
    AutoField
    0.56
     Coast
    0.54
    eburger
    0.53
    úcar
    0.52
    ).__
    0.52
     hoàng
    0.50
    Rujuakan
    0.49
    epar
    0.49
     COAST
    0.48
     coast
    0.48
    Activations Density 0.849%

    No Known Activations