© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13699
    Prev
    Next
    INDEX
    Explanations

    words related to a physical location or community as well as associated characteristics

    oai_token-act-pair · gemini-2.0-flash

    assume

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Cæsar
    -0.62
    URLException
    -0.59
     Phry
    -0.56
     Planta
    -0.54
     Ronde
    -0.52
    apunov
    -0.52
     Telex
    -0.52
     Wittenberg
    -0.52
     ſtand
    -0.50
     deſt
    -0.50
    POSITIVE LOGITS
     assume
    1.34
     assumes
    1.23
     acquire
    1.23
     acquires
    1.14
     assuming
    1.07
     acquired
    1.06
     acquiring
    1.04
     assumed
    1.04
    assume
    1.00
     adqui
    0.95
    Activations Density 4.471%

    No Known Activations