© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10746
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "spook" or "spoof"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Global
    -0.55
    tse
    -0.50
    Global
    -0.49
     vers
    -0.47
     __
    -0.47
     mele
    -0.47
     boca
    -0.46
    itans
    -0.46
     مواليد
    -0.46
     tres
    -0.45
    POSITIVE LOGITS
    tvguidetime
    0.84
    #+#
    0.71
     resourceCulture
    0.68
     @"/
    0.66
    [++
    0.60
    VersionUID
    0.59
     Administrativna
    0.59
    TintMode
    0.59
     ―――――
    0.58
    IUrlHelper
    0.57
    Activations Density 0.145%

    No Known Activations