© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5952
    Prev
    Next
    INDEX
    Explanations

    words and phrases about learning, research and comparison

    oai_token-act-pair · gemini-2.0-flash

    Instructions/Application Usage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    帖最后由
    -1.05
    __":
    -1.02
    ValueStyle
    -1.02
    Datuak
    -1.00
     الحره
    -0.99
     صوتيه
    -0.96
    Rüyada
    -0.92
    
    -0.90
    KommentareTeilen
    -0.90
     MainAxisSize
    -0.88
    POSITIVE LOGITS
     using
    0.44
     
    0.41
    ann
    0.40
    i
    0.40
    a
    0.37
    lah
    0.36
     n
    0.35
    n
    0.35
    ij
    0.35
    ↵
    0.34
    Activations Density 4.991%

    No Known Activations