© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5383
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and sentence delimiters

    oai_token-act-pair · gemini-2.0-flash

    words with archaic or unusual spelling

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

    ellipses

    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
     snippetHide
    -0.70
    hematical
    -0.67
    …
    -0.67
    umbnail
    -0.65
    naphthal
    -0.65
    iffance
    -0.64
    ratulations
    -0.64
    ...
    -0.63
    nesc
    -0.61
    glEnd
    -0.60
    POSITIVE LOGITS
     houſe
    0.67
     uſed
    0.62
     ſaid
    0.62
     juſ
    0.61
     quæ
    0.59
     Houſe
    0.59
     mukana
    0.58
     ſtre
    0.57
     ſeveral
    0.57
     theſe
    0.55
    Activations Density 3.173%

    No Known Activations