© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11407
    Prev
    Next
    INDEX
    Explanations

    geographic regions in Germany

    oai_token-act-pair · gemini-2.0-flash

    German places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Personensuche
    -0.45
     Meta
    -0.45
     unknownFields
    -0.44
    didSet
    -0.44
     MediatR
    -0.42
    $_['
    -0.42
     aca
    -0.40
     client
    -0.39
     sdf
    -0.39
     Arti
    -0.39
    POSITIVE LOGITS
     esternos
    0.82
    انيف
    0.66
     Roskov
    0.63
     bonté
    0.59
     survie
    0.59
     odkazy
    0.59
     culturelles
    0.58
     vapeur
    0.58
    帖最后由
    0.58
    AutoScaleMode
    0.57
    Activations Density 1.368%

    No Known Activations