© 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. 9950
    Prev
    Next
    INDEX
    Explanations

    mentions of age and numerical ranges

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers or tags in various languages

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

    age

    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
    __':
    -0.63
    __":
    -0.54
    gemeester
    -0.52
     Lanes
    -0.52
    MTL
    -0.48
    kette
    -0.48
    Filmographie
    -0.48
     sportivo
    -0.47
    noks
    -0.47
    lemma
    -0.47
    POSITIVE LOGITS
    Enllaces
    0.82
     متعلقه
    0.69
     مرئيه
    0.67
    tagHelper
    0.67
     صوتيه
    0.65
    (!__
    0.64
    archiviato
    0.60
     оригіналу
    0.60
    serviceWorker
    0.59
     pinulongan
    0.58
    Activations Density 0.965%

    No Known Activations