© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7993
    Prev
    Next
    INDEX
    Explanations

    greek letters and math symbols

    oai_token-act-pair · gemini-2.0-flash

    mathematical symbols and notation

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

    mathematical code

    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
    Datuak
    -0.74
     HasFactory
    -0.71
    NameInMap
    -0.65
    uxxxx
    -0.65
    featureID
    -0.62
    Jeografia
    -0.60
    DllImport
    -0.59
     AssemblyCulture
    -0.59
    
    -0.58
    cèse
    -0.57
    POSITIVE LOGITS
    первых
    0.52
    жели
    0.51
    Leaks
    0.49
    IsContent
    0.47
     Grimal
    0.46
     vacacionales
    0.46
     velours
    0.46
    ماذا
    0.45
    Optimizer
    0.45
     animale
    0.44
    Activations Density 1.548%

    No Known Activations