© 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. 11745
    Prev
    Next
    INDEX
    Explanations

    descriptions of scenery, especially the night sky

    oai_token-act-pair · gemini-2.0-flash

    Stars and lights

    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
    Gambas
    -0.61
    WaitGroup
    -0.59
    schutz
    -0.59
     ostavi
    -0.58
    TRAS
    -0.58
    الحياه
    -0.58
    zwungen
    -0.57
     насељу
    -0.57
     افزار
    -0.57
    saida
    -0.56
    POSITIVE LOGITS
    mur
    0.49
     jac
    0.47
    TestingModule
    0.45
     shooting
    0.45
     PNP
    0.44
     Stell
    0.43
     kona
    0.43
     éto
    0.43
     buds
    0.42
    género
    0.42
    Activations Density 2.521%

    No Known Activations