© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11414
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to providing information or contacting someone.

    oai_token-act-pair · gemini-2.0-flash

    contact

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     clear
    -1.20
    clear
    -1.04
     Clear
    -0.96
    Clear
    -0.94
     CLEAR
    -0.84
     claros
    -0.79
     claro
    -0.78
    CLEAR
    -0.77
     klar
    -0.75
     chiaro
    -0.75
    POSITIVE LOGITS
     details
    1.45
     information
    1.27
     Details
    1.21
    details
    1.18
    Details
    1.13
    information
    1.07
     particulars
    1.05
     info
    1.04
     detail
    1.03
     DETAILS
    1.02
    Activations Density 1.005%

    No Known Activations