© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2761
    Prev
    Next
    INDEX
    Explanations

    geographic locations and governmental bodies, especially counties and towns in North Carolina, as well as roadways.

    oai_token-act-pair · gemini-2.0-flash

    Place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    enterOuterAlt
    -0.65
    brities
    -0.61
     dAtA
    -0.59
    AddHtmlAttribute
    -0.58
    FundMe
    -0.58
    )");
    -0.58
    istice
    -0.57
    ergies
    -0.57
     }}$}
    -0.56
     Monfieur
    -0.56
    POSITIVE LOGITS
    లాలు
    0.56
     Buffalo
    0.53
     Allegheny
    0.46
    villa
    0.46
     Damascus
    0.45
     Meadow
    0.44
    Bel
    0.44
     Bel
    0.43
     reta
    0.43
     Nebraska
    0.42
    Activations Density 3.515%

    No Known Activations