© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5348
    Prev
    Next
    INDEX
    Explanations

    pieces of data within JSON-like structures, particularly those dealing with calendar-related information and potentially another language

    oai_token-act-pair · gemini-2.0-flash

    uncommon or archaic words

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

    ","

    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
    ,
    -0.68
     ,
    -0.62
    </em>
    -0.59
    </strong>
    -0.55
    goto
    -0.52
    ,"
    -0.52
    àn
    -0.52
    ","
    -0.50
    .,
    -0.50
    ,”
    -0.50
    POSITIVE LOGITS
     itſelf
    0.77
     Monfieur
    0.76
     MessageBoxIcon
    0.74
     resourceCulture
    0.71
     faſt
    0.71
     Theſe
    0.67
    BASEPATH
    0.65
     Beſ
    0.65
    postolic
    0.64
     becauſe
    0.64
    Activations Density 5.334%

    No Known Activations