© 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. 1727
    Prev
    Next
    INDEX
    Explanations

    locations and strings of words related to locations

    oai_token-act-pair · gemini-2.0-flash

    Locations, organizations, 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_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
     Económica
    -0.79
    MergeFrom
    -0.74
     Monfieur
    -0.69
    TagMode
    -0.68
     CHAPITRE
    -0.68
    RegistryLite
    -0.65
     تانيه
    -0.65
     الحره
    -0.64
     Escolar
    -0.63
     ſch
    -0.63
    POSITIVE LOGITS
    évaluateur
    0.53
    Vidite
    0.53
     Hotel
    0.52
     Autorizaciones
    0.47
     Colle
    0.47
     Super
    0.46
     Sto
    0.45
     Cole
    0.45
     Union
    0.44
     List
    0.44
    Activations Density 1.348%

    No Known Activations