© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8924
    Prev
    Next
    INDEX
    Explanations

    words related to data analysis

    oai_token-act-pair · gemini-2.0-flash

    terms related to levels or rates

    np_token-act-pair-logits · gpt-4o-mini

    Rates and levels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    +#+#
    -0.84
     surla
    -0.68
     MainAxisSize
    -0.61
    AccessorTable
    -0.59
     صوتيه
    -0.57
    #+#
    -0.56
     nationalities
    -0.54
    IInterface
    -0.54
    BoxShadow
    -0.54
    
    -0.54
    POSITIVE LOGITS
     rate
    1.55
     level
    1.50
     levels
    1.34
    rate
    1.25
     Rate
    1.21
     rates
    1.20
    level
    1.20
     RATE
    1.16
     Level
    1.15
    Rate
    1.14
    Activations Density 5.168%

    No Known Activations