© 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. 7580
    Prev
    Next
    INDEX
    Explanations

    scientific discourse about chemical bonds and spectra

    oai_token-act-pair · gemini-2.0-flash

    foreign language or specialized terminology

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

    Foreign words

    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
    ChildScrollView
    -0.79
    ftagPool
    -0.77
    tvguidetime
    -0.77
     nakalista
    -0.76
    OrBuilder
    -0.71
     surla
    -0.71
    ThroughAttribute
    -0.66
    InitVars
    -0.65
    >//
    -0.62
    Rüyada
    -0.62
    POSITIVE LOGITS
     numerus
    0.48
     he
    0.47
     esempi
    0.45
     refroidissement
    0.44
    jár
    0.44
    ジェクト
    0.44
     Volkes
    0.43
    informationen
    0.43
     defesa
    0.41
    ACGIH
    0.41
    Activations Density 1.029%

    No Known Activations