© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1250
    Prev
    Next
    INDEX
    Explanations

    words and phrases regarding appreciation or lack thereof, and expressions of anger or regret.

    oai_token-act-pair · gemini-2.0-flash

    appreciation and gratitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RenderAtEndOf
    -0.59
     BoxDecoration
    -0.58
    日閲覧
    -0.55
    etine
    -0.52
    FormState
    -0.52
    iastes
    -0.52
    ferd
    -0.49
    erdin
    -0.49
    CGRectMake
    -0.49
     smelled
    -0.48
    POSITIVE LOGITS
    TestingModule
    0.53
    thâu
    0.53
    Reentrant
    0.51
    ודם
    0.51
    MetaType
    0.50
     vulgaris
    0.48
     generali
    0.47
    CHP
    0.47
     poly
    0.46
     Pologne
    0.46
    Activations Density 0.815%

    No Known Activations