© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1450
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and financial arguments, particularly related to evidence and outcomes based on assumptions.

    oai_token-act-pair · gemini-2.0-flash

    conditional language

    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
     sekal
    -0.57
    insegna
    -0.51
    öpf
    -0.47
     prefixed
    -0.46
    QMetaType
    -0.45
    xito
    -0.44
    Kontrola
    -0.44
    planung
    -0.43
    quence
    -0.43
    Билгалдахарш
    -0.42
    POSITIVE LOGITS
     disambiguazione
    0.91
    astify
    0.66
     "..\..\..\
    0.66
    PerformLayout
    0.65
    })));
    0.64
    ViewFeatures
    0.64
    brainly
    0.63
     архивлан
    0.62
    المناصب
    0.62
     "..\..\
    0.61
    Activations Density 29.939%

    No Known Activations