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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11175
    Prev
    Next
    INDEX
    Explanations

    instances of "to" followed by a verb in the infinitive form and positive adjectives.

    oai_token-act-pair · gemini-2.0-flash

    Tutorial documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Aid
    -0.50
    kaido
    -0.50
    SpringBootTest
    -0.49
    Reach
    -0.48
     Care
    -0.47
    mögens
    -0.46
     care
    -0.45
     Reach
    -0.45
    ográfica
    -0.45
    loy
    -0.44
    POSITIVE LOGITS
    ագրություններ
    0.66
    ConstraintMaker
    0.64
    MigrationBuilder
    0.64
    AnchorStyles
    0.61
    دانشنامهٔ
    0.60
    RegistryLite
    0.60
    rungsseite
    0.60
    SPATH
    0.59
    QMetaType
    0.59
    :✨
    0.58
    Activations Density 1.806%

    No Known Activations