© 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. 14772
    Prev
    Next
    INDEX
    Explanations

    text discussing different options, their benefits and drawbacks

    oai_token-act-pair · gemini-2.0-flash

    nonsensical or unique words

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

    advantages and disadvantages

    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
    AndEndTag
    -0.76
     بيها
    -0.69
    ंदीखरीदारी
    -0.66
    tvguidetime
    -0.65
     שוליים
    -0.62
    帖最后由
    -0.62
    modelBuilder
    -0.62
    ">//
    -0.60
    ніципалі
    -0.59
    limit
    -0.57
    POSITIVE LOGITS
    owol
    0.61
    PHONY
    0.61
    )_/¯
    0.55
    Datuak
    0.52
    turo
    0.52
    schild
    0.52
    ElementException
    0.51
    elung
    0.50
    ┬
    0.49
    asantry
    0.48
    Activations Density 1.325%

    No Known Activations