© 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. 427
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of how a football/soccer team is playing, sometimes with some negative language included as well

    oai_token-act-pair · gemini-2.0-flash

    Soccer/Football

    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
    windowFixed
    -0.97
    LayoutPanel
    -0.79
    StackNavigator
    -0.68
    sizeCache
    -0.65
     חיצוניים
    -0.65
    __':
    -0.65
    COUVER
    -0.65
    PerformLayout
    -0.64
    AppMethodBeat
    -0.61
     '\\;'
    -0.60
    POSITIVE LOGITS
     sim
    0.46
    حياته
    0.46
    detectChanges
    0.42
    乏
    0.40
     tense
    0.40
     deadlock
    0.40
     caution
    0.38
    گیر
    0.38
     cường
    0.37
     camp
    0.37
    Activations Density 0.442%

    No Known Activations