© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3304
    Prev
    Next
    INDEX
    Explanations

    words related to describing locations like cemeteries, properties, or states

    oai_token-act-pair · gemini-2.0-flash

    coding and cemeteries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    cektir
    -0.59
     gynnwys
    -0.56
    apimachinery
    -0.54
    oa̍t
    -0.53
     Référence
    -0.52
    Хьажоргаш
    -0.52
    Сылтамалар
    -0.52
    PageFactory
    -0.51
    Derbyniad
    -0.51
    WithTag
    -0.50
    POSITIVE LOGITS
    EFAULT
    0.49
    createStatement
    0.49
    LayoutConstraint
    0.49
    shaded
    0.48
    sorption
    0.47
    CURLOPT
    0.47
    DeleteBehavior
    0.47
    Private
    0.46
    בית
    0.45
    prepareStatement
    0.45
    Activations Density 0.410%

    No Known Activations