© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13766
    Prev
    Next
    INDEX
    Explanations

    phrases that describe enthusiasm or positive sentiment, frequently using the word "with"

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ModelRenderer
    -0.54
    estacks
    -0.53
    TestBed
    -0.50
    portál
    -0.50
    argout
    -0.50
    曖昧さ回避
    -0.50
    ütü
    -0.49
    ugc
    -0.48
    QMetaType
    -0.48
     regime
    -0.47
    POSITIVE LOGITS
    RectangleBorder
    0.62
    }';
    0.60
    UserScript
    0.54
    resaid
    0.53
    quiao
    0.50
     gleichen
    0.50
    loroethane
    0.49
    registrer
    0.49
    ranton
    0.47
     Viitattu
    0.46
    Activations Density 0.627%

    No Known Activations