© 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. 9467
    Prev
    Next
    INDEX
    Explanations

    caveats to previous statements

    oai_token-act-pair · gemini-2.0-flash

    punctuation and transitions

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

    comma

    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
    TagHelper
    -0.88
     kasarigan
    -0.81
    Искәрмәләр
    -0.77
     intptr
    -0.70
     الحره
    -0.65
    Lähteet
    -0.64
     []),
    -0.64
    WriteAttribute
    -0.63
    "]]
    -0.63
    enumi
    -0.62
    POSITIVE LOGITS
    ,
    2.19
    ，
    0.61
     ,
    0.54
    ،
    0.54
     however
    0.49
     tuttavia
    0.47
    ,(
    0.46
    ,{
    0.45
    .,
    0.43
     thus
    0.43
    Activations Density 2.910%

    No Known Activations