© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12776
    Prev
    Next
    INDEX
    Explanations

    sentences including auxiliary verbs and common conjunctions

    oai_token-act-pair · gemini-2.0-flash

    technical or code-related terms

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

    be

    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
     inoxydable
    -0.59
     powiedzieć
    -0.52
     Turku
    -0.46
     Erzb
    -0.46
    ovas
    -0.45
    vő
    -0.45
     peint
    -0.45
    átku
    -0.44
    uilla
    -0.44
     kuwa
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.75
    twimg
    0.72
    rungsseite
    0.68
    +#+#
    0.63
     '\\;'
    0.63
     betweenstory
    0.61
     protoimpl
    0.61
     resourceCulture
    0.60
    didSet
    0.60
     Waray
    0.60
    Activations Density 0.840%

    No Known Activations