© 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. 4896
    Prev
    Next
    INDEX
    Explanations

    phrases which establish existence.

    oai_token-act-pair · gemini-2.0-flash

    various pronouns and linking words

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

    there

    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
     CreateTagHelper
    -0.96
     disambiguazione
    -0.76
    DoubleQuotes
    -0.75
    évaluateur
    -0.72
    GOTREF
    -0.68
    awtextra
    -0.66
    osoba
    -0.63
     referenties
    -0.62
     '\\;'
    -0.61
     ویکی‌پدی
    -0.59
    POSITIVE LOGITS
    pecies
    0.45
    zä
    0.43
     gants
    0.41
    entraînement
    0.40
    Dear
    0.39
    下一篇
    0.39
     stabilité
    0.39
    menina
    0.38
    ervé
    0.38
     frattempo
    0.38
    Activations Density 0.178%

    No Known Activations