© 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. 15573
    Prev
    Next
    INDEX
    Explanations

    statistics and high or low scores over time

    oai_token-act-pair · gemini-2.0-flash

    high measurements and risk

    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
     High
    -2.72
    High
    -2.72
     high
    -2.61
    high
    -2.59
     HIGH
    -2.38
    HIGH
    -2.36
     highest
    -2.16
    Higher
    -2.08
     Higher
    -2.08
     Highest
    -2.02
    POSITIVE LOGITS
    ftagPool
    0.75
     eventdata
    0.65
    enumi
    0.64
    脚注の使い方
    0.60
    ConstraintMaker
    0.54
     esternos
    0.54
    enumii
    0.54
     onCreateView
    0.53
    
    0.52
    adaptiveStyles
    0.51
    Activations Density 4.545%

    No Known Activations