© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15937
    Prev
    Next
    INDEX
    Explanations

    mentions of recreational trails and paths

    oai_token-act-pair · gemini-2.0-flash

    trail

    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
    InputBorder
    -0.64
    tonsoft
    -0.62
    Carriera
    -0.62
    CONSIN
    -0.61
    jetbrains
    -0.59
    walla
    -0.58
    OPHY
    -0.57
    ardless
    -0.57
     TextInputType
    -0.57
    etheless
    -0.56
    POSITIVE LOGITS
    /**
    0.74
    RenderAtEndOf
    0.71
     nahilalakip
    0.69
     mukana
    0.69
     colorés
    0.68
     científicas
    0.65
     myſelf
    0.65
     químicas
    0.65
    expandindo
    0.65
     coloré
    0.64
    Activations Density 0.619%

    No Known Activations