© 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. 8202
    Prev
    Next
    INDEX
    Explanations

    computer code and architecture references

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'x' or 'X'

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

    x

    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
    Hozzáférés
    -0.67
    enumii
    -0.63
    specialchars
    -0.62
    esgue
    -0.59
    ļu
    -0.57
    enumi
    -0.56
    Einzelnachweise
    -0.54
     <=",
    -0.54
     jScrollPane
    -0.54
    IndentedString
    -0.54
    POSITIVE LOGITS
     MainAxisSize
    0.51
    eradish
    0.50
    исленность
    0.49
    tagHelperRunner
    0.48
    rungsseite
    0.47
    usermodel
    0.46
    unción
    0.45
    sels
    0.44
     Blythe
    0.44
    textLabel
    0.43
    Activations Density 0.466%

    No Known Activations