© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8685
    Prev
    Next
    INDEX
    Explanations

    percentages, especially those mentioning groups of people

    oai_token-act-pair · gemini-2.0-flash

    Statistic references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    line
    -0.48
    run
    -0.45
     Halb
    -0.44
     run
    -0.43
    रा
    -0.41
     NavController
    -0.40
    قامة
    -0.39
    raded
    -0.38
    lines
    -0.38
     PopupWindow
    -0.38
    POSITIVE LOGITS
    IntoConstraints
    0.74
    
    0.72
    //
    0.69
    MessageTagHelper
    0.69
    AndEndTag
    0.69
    /*
    0.63
     nakalista
    0.61
    Composable
    0.61
     unknownFields
    0.60
    Kjelder
    0.60
    Activations Density 24.856%

    No Known Activations