© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6816
    Prev
    Next
    INDEX
    Explanations

    instances of the words "direct" and "indirect", particularly as they relate to parental involvement, claims, queries or examples.

    oai_token-act-pair · gemini-2.0-flash

    indirect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nahilalakip
    -1.05
    tagext
    -0.97
    Personendaten
    -0.94
    PreferredItem
    -0.78
    Personensuche
    -0.77
    +:+
    -0.76
     للاسماء
    -0.75
    Collegamenti
    -0.73
    Portale
    -0.72
    dafx
    -0.71
    POSITIVE LOGITS
    Hole
    0.60
     Ches
    0.57
    ेशन
    0.56
     Anges
    0.54
     Hole
    0.54
    kreuz
    0.54
    AutoField
    0.52
     balon
    0.51
     Hur
    0.51
    es
    0.51
    Activations Density 1.587%

    No Known Activations