© 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. 15702
    Prev
    Next
    INDEX
    Explanations

    locations in Poland or real estate listings

    oai_token-act-pair · gemini-2.0-flash

    Locations and geographical regions

    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
    im
    -0.41
     im
    -0.40
    ╝
    -0.39
    逆
    -0.38
    Timothy
    -0.38
    dist
    -0.38
     Michael
    -0.37
    du
    -0.37
    mybatisplus
    -0.37
    rums
    -0.37
    POSITIVE LOGITS
    DockStyle
    0.83
    FormTagHelper
    0.81
    ⓧ
    0.75
     Superhost
    0.73
    Geplaatst
    0.71
    OGND
    0.70
     surla
    0.69
    Климат
    0.69
    ürtel
    0.68
     beachfront
    0.68
    Activations Density 8.277%

    No Known Activations