© 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. 5399
    Prev
    Next
    INDEX
    Explanations

    text in languages other than English which includes requests and explanations

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
    BeginContext
    -0.59
    Datuak
    -0.57
     circumstances
    -0.54
     circonstances
    -0.52
     União
    -0.50
     free
    -0.50
    itze
    -0.49
    trine
    -0.48
     by
    -0.48
    padek
    -0.48
    POSITIVE LOGITS
    WithIOException
    0.83
     gynhyrchwyd
    0.73
     дописавши
    0.72
     فريبيس
    0.66
     mergeFrom
    0.62
     
    0.60
    tagHelperRunner
    0.60
    /******/
    0.58
    SequentialGroup
    0.57
     Taktlose
    0.57
    Activations Density 1.607%

    No Known Activations