© 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. 11521
    Prev
    Next
    INDEX
    Explanations

    references to articles, essays, blogs, and reporting, often including possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    unusual or unique word forms

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

    writings and publications

    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
    jos
    -0.41
     «
    -0.40
     D
    -0.40
    「
    -0.40
    /**
    -0.39
    D
    -0.39
    dza
    -0.38
    mak
    -0.38
    mb
    -0.38
    ũ
    -0.37
    POSITIVE LOGITS
     Anſ
    0.71
     myſelf
    0.70
     Мексичка
    0.69
     NSCoder
    0.68
    ANSA
    0.68
    InputBorder
    0.67
     Arund
    0.66
     eulogy
    0.66
    FTFY
    0.65
    KEYCODE
    0.65
    Activations Density 3.803%

    No Known Activations