© 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. 11673
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes and shortened words

    oai_token-act-pair · gemini-2.0-flash

    non-standard text formats or code snippets

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

    code and identifiers

    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
    f
    -0.65
    full
    -0.54
    enumi
    -0.51
    ful
    -0.50
    elemField
    -0.50
    fice
    -0.49
    fulness
    -0.49
    ications
    -0.48
    ituary
    -0.47
    fu
    -0.47
    POSITIVE LOGITS
    sizeCache
    0.61
    __":
    0.60
     continúas
    0.57
    AndEndTag
    0.56
    providedIn
    0.56
     &___
    0.54
    хьтан
    0.54
    '&:
    0.52
     protoimpl
    0.52
    oneofs
    0.52
    Activations Density 1.746%

    No Known Activations