© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6383
    Prev
    Next
    INDEX
    Explanations

    sentence fragments with various verb conjugations

    oai_token-act-pair · gemini-2.0-flash

    likelihood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Paglinawan
    -0.73
     GenerationType
    -0.69
    esterno
    -0.56
    MergeFrom
    -0.54
    @__
    -0.52
    bní
    -0.52
    UTRAL
    -0.52
    NameInMap
    -0.52
     moindre
    -0.51
    ImGui
    -0.50
    POSITIVE LOGITS
     probably
    2.33
     likely
    2.25
    probably
    2.11
     Probably
    2.08
    Probably
    2.05
    likely
    1.98
     Likely
    1.88
    Likely
    1.74
     probabilmente
    1.72
     provavelmente
    1.69
    Activations Density 1.496%

    No Known Activations