© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6300
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, especially in Indonesia

    oai_token-act-pair · gemini-2.0-flash

    Southeast Asia locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    __':
    -0.63
    CompilerServices
    -0.57
    וויק
    -0.53
     Vals
    -0.53
    Contributed
    -0.50
    rawDesc
    -0.50
    __':
    -0.50
    HasKey
    -0.48
    త్ర
    -0.48
     Reactivity
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.53
    aarrggbb
    0.51
     Roskov
    0.50
     CWE
    0.50
    #+#
    0.50
    Pojo
    0.49
    Autoritní
    0.49
    出版年
    0.47
    Java
    0.47
    PerformLayout
    0.47
    Activations Density 0.636%

    No Known Activations