© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13255
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating continuation or improvement

    oai_token-act-pair · gemini-2.0-flash

    continuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    SharedDtor
    -0.66
    ellidos
    -0.66
     télévisée
    -0.65
    RenderAtEndOf
    -0.65
    MessageOf
    -0.64
     الحره
    -0.61
    bootstrapcdn
    -0.60
    CodeAttribute
    -0.59
    LookAnd
    -0.59
     متعلقه
    -0.59
    POSITIVE LOGITS
    NameInMap
    0.69
    AddHtmlAttribute
    0.61
     recul
    0.53
    paramInt
    0.49
    исленность
    0.48
    ос
    0.46
     crescita
    0.46
     updates
    0.46
    Updates
    0.45
     concerns
    0.45
    Activations Density 4.344%

    No Known Activations