© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2263
    Prev
    Next
    INDEX
    Explanations

    words that are used to count or quantify multiple things

    oai_token-act-pair · gemini-2.0-flash

    parts and sides

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     each
    -0.96
     both
    -0.91
     EACH
    -0.90
    Each
    -0.88
     Each
    -0.88
    both
    -0.82
    Both
    -0.82
     Both
    -0.81
    each
    -0.81
    EACH
    -0.76
    POSITIVE LOGITS
     parts
    0.73
    DockStyle
    0.71
     types
    0.71
     sides
    0.70
     levels
    0.69
     side
    0.64
     forms
    0.60
    parts
    0.58
    part
    0.57
     directions
    0.57
    Activations Density 1.891%

    No Known Activations