© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13703
    Prev
    Next
    INDEX
    Explanations

    language describing motorcycles

    oai_token-act-pair · gemini-2.0-flash

    technology and vehicles

    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
    Espèce
    -0.79
    GraphicsUnit
    -0.73
    WriteLiteral
    -0.71
    nodoc
    -0.71
    AutoresizingMask
    -0.67
     Brand
    -0.66
    yelitis
    -0.66
    imageshack
    -0.66
    ModelSerializer
    -0.63
    Portály
    -0.62
    POSITIVE LOGITS
     виправивши
    0.58
     crane
    0.45
     cranes
    0.41
     Blockly
    0.41
     potash
    0.40
     SFR
    0.40
     undone
    0.39
     działa
    0.39
    traje
    0.39
     možno
    0.39
    Activations Density 6.779%

    No Known Activations