© 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. 7309
    Prev
    Next
    INDEX
    Explanations

    sentences and phrases used in opinions that express how an author feels

    oai_token-act-pair · gemini-2.0-flash

    diverse and complex expressions in multiple languages

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

    period

    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
     work
    -0.44
    or
    -0.44
    ma
    -0.43
    not
    -0.42
    com
    -0.42
     bruk
    -0.42
    us
    -0.41
    ró
    -0.41
    D
    -0.41
    pe
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    1.04
    ंदीखरीदारी
    1.00
    +#+#
    0.96
     autorytatywna
    0.94
    yntaxException
    0.91
    AlterField
    0.87
     ویکی‌پدیا
    0.86
     дописавши
    0.84
    Personensuche
    0.84
    expandindo
    0.84
    Activations Density 2.519%

    No Known Activations