© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5695
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "actually" but also can activate on pronouns and forms of the verb to be.

    oai_token-act-pair · gemini-2.0-flash

    say "a" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    JpaRepository
    -0.60
    DockStyle
    -0.59
    AddField
    -0.54
    RTLD
    -0.52
    AntiForgeryToken
    -0.49
     CreateTagHelper
    -0.49
    ochrom
    -0.47
    ResumeLayout
    -0.45
    idious
    -0.45
    asteel
    -0.45
    POSITIVE LOGITS
     very
    1.17
    very
    1.11
    Very
    1.07
     Very
    1.03
     quite
    1.00
     really
    0.94
     extremely
    0.91
     muy
    0.91
    quite
    0.89
     oldukça
    0.89
    Activations Density 2.782%

    No Known Activations