© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11135
    Prev
    Next
    INDEX
    Explanations

    mentions of Indian place names, particularly in Andhra Pradesh, and educational institutions

    oai_token-act-pair · gemini-2.0-flash

    Vizianagaram (place)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.07
     whoſe
    -0.69
     reaſon
    -0.66
    NewUrlParser
    -0.63
     himſelf
    -0.61
     neceſſ
    -0.61
     pleaſure
    -0.61
     itſelf
    -0.60
     themſelves
    -0.58
     Cæsar
    -0.58
    POSITIVE LOGITS
    =’
    0.47
    astan
    0.47
     tục
    0.46
    putan
    0.45
    hoea
    0.45
    oiseau
    0.45
     "..\..\
    0.43
    EndContext
    0.42
     birds
    0.41
    Verte
    0.41
    Activations Density 0.357%

    No Known Activations