© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12180
    Prev
    Next
    INDEX
    Explanations

    words used in recounting a story

    oai_token-act-pair · 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
     дописавши
    -0.57
    routeProvider
    -0.57
     препратки
    -0.56
     Infórmanos
    -0.54
     Winaray
    -0.54
     OFDb
    -0.53
    marshaller
    -0.51
     compared
    -0.51
    #+#
    -0.51
     BoxDecoration
    -0.49
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.55
     Wicidata
    0.54
    wär
    0.53
     vayas
    0.52
    tagext
    0.50
     AlertDialog
    0.50
    ItemBackground
    0.49
    sphinx
    0.49
     diffé
    0.47
     ink
    0.47
    Activations Density 3.689%

    No Known Activations