© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    words related to ecology and wildlife

    oai_token-act-pair · gemini-2.0-flash

    words starting with 'b' or 'd'

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

    marsh environment

    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
     myſelf
    -0.88
    GEBURTSDATUM
    -0.79
     itſelf
    -0.77
     poffible
    -0.75
     ModelExpression
    -0.74
    OGND
    -0.73
     AssemblyCulture
    -0.72
     himſelf
    -0.71
    DockStyle
    -0.71
    Vidite
    -0.71
    POSITIVE LOGITS
     cu
    0.50
    ói
    0.49
     bekas
    0.48
     sw
    0.47
    double
    0.47
     bit
    0.47
    DUR
    0.47
    Double
    0.46
     Bit
    0.45
     Th
    0.45
    Activations Density 0.923%

    No Known Activations