© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7875
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating a timeline or specific date.

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     Barclay
    -0.50
    RTEX
    -0.48
     arrived
    -0.48
    reonine
    -0.48
     arriving
    -0.46
     ModelRenderer
    -0.45
    issex
    -0.45
    Trail
    -0.45
    arrived
    -0.45
     arrive
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.76
     kasarigan
    0.75
    tagHelperRunner
    0.63
    vosť
    0.63
     surla
    0.61
     Roskov
    0.60
     disponibilités
    0.57
    ValueStyle
    0.57
    ագրություններ
    0.55
    كويكب
    0.54
    Activations Density 0.516%

    No Known Activations