© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11356
    Prev
    Next
    INDEX
    Explanations

    code related to testing

    oai_token-act-pair · gemini-2.0-flash

    programming function definitions

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

    Javascript code

    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
     Brant
    -0.47
     netts
    -0.45
    Output
    -0.44
    Special
    -0.43
    Props
    -0.41
    laration
    -0.41
    Close
    -0.41
    uarts
    -0.41
    OPP
    -0.41
     censi
    -0.41
    POSITIVE LOGITS
     يتيمه
    0.78
     EconPapers
    0.70
    MLLoader
    0.68
     function
    0.67
     Bioaccumulative
    0.63
     Monfieur
    0.63
     jsPsych
    0.62
    encodeWith
    0.59
    enterOuterAlt
    0.57
    WriteTagHelper
    0.57
    Activations Density 4.333%

    No Known Activations