© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10352
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel-related information and planning, and some negative sentiment.

    oai_token-act-pair · gemini-2.0-flash

    where

    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
     Location
    -0.77
     Locations
    -0.71
    OGND
    -0.70
     location
    -0.69
     destination
    -0.69
     Destination
    -0.68
     LOCATION
    -0.64
    Location
    -0.64
     destinations
    -0.62
     locations
    -0.61
    POSITIVE LOGITS
     where
    1.63
    where
    1.41
    Where
    1.29
     Where
    1.20
     où
    1.16
     donde
    1.14
     WHERE
    1.06
     где
    1.00
    WHERE
    0.93
    donde
    0.93
    Activations Density 3.935%

    No Known Activations