© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9684
    Prev
    Next
    INDEX
    Explanations

    geographic features and locations.

    oai_token-act-pair · gemini-2.0-flash

    geographical 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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ändert
    -0.55
     IBOutlet
    -0.52
     ThemeData
    -0.49
    udara
    -0.49
    antle
    -0.48
    #+#
    -0.48
     SUBST
    -0.46
    didSet
    -0.46
    WebElementEntity
    -0.44
    zám
    -0.44
    POSITIVE LOGITS
    Atsauces
    0.68
    Билгалдахарш
    0.66
    SharedDtor
    0.64
     referenties
    0.61
    où
    0.59
    uxxxx
    0.59
    kháu
    0.59
     where
    0.58
     intptr
    0.57
    expandindo
    0.57
    Activations Density 2.071%

    No Known Activations