© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12841
    Prev
    Next
    INDEX
    Explanations

    verbs or nouns indicating action or decisions that could drive a plot forward.

    oai_token-act-pair · gemini-2.0-flash

    actions and events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ритори
    -0.41
     dés
    -0.40
     nặng
    -0.40
     htons
    -0.39
     Medidas
    -0.38
    jenie
    -0.38
    medi
    -0.38
    νον
    -0.38
    Mad
    -0.37
     करती
    -0.37
    POSITIVE LOGITS
    queryInterface
    0.75
     nahilalakip
    0.70
    IUrlHelper
    0.69
    featureID
    0.69
    utex
    0.66
    (&:
    0.66
    RegressionTest
    0.65
    RTEE
    0.64
    مصادر
    0.61
    Their
    0.61
    Activations Density 2.782%

    No Known Activations