© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13601
    Prev
    Next
    INDEX
    Explanations

    the substrings "ize", "kin", and "oft", possibly in the context of URLs, code, and file formats

    oai_token-act-pair · gemini-2.0-flash

    ize and kin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Sat
    -0.68
     Sat
    -0.62
     rând
    -0.58
     pourtant
    -0.56
     sat
    -0.55
     însă
    -0.55
    følgelig
    -0.54
     rodea
    -0.54
    erdings
    -0.54
    jface
    -0.54
    POSITIVE LOGITS
    DockStyle
    0.85
     defaultstate
    0.63
    
    0.62
    delwed
    0.60
    SourceChecksum
    0.58
    NewGuid
    0.55
    featureID
    0.54
     BorderRadius
    0.54
    pectiva
    0.54
    MLLoader
    0.53
    Activations Density 0.358%

    No Known Activations