© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6092
    Prev
    Next
    INDEX
    Explanations

    general words used with opinions

    oai_token-act-pair · gemini-2.0-flash

    archaic or stylized English words

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

    have

    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
    
    -0.56
    __':
    -0.51
    __':
    -0.50
    WEBPACK
    -0.50
    ])]
    -0.48
     lohnt
    -0.47
     karet
    -0.46
     llevaron
    -0.46
     pega
    -0.46
    
    -0.45
    POSITIVE LOGITS
     Efq
    0.76
     Theſe
    0.74
     houſe
    0.74
     Houſe
    0.73
     ſeveral
    0.71
     ſta
    0.71
     Jefus
    0.71
     ſtate
    0.70
    wiſe
    0.69
     myſelf
    0.69
    Activations Density 2.747%

    No Known Activations