© 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. 14018
    Prev
    Next
    INDEX
    Explanations

    words associated with the scientific or academic fields, and logical connectives.

    oai_token-act-pair · gemini-2.0-flash

    and

    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
    udert
    -0.59
    }:${
    -0.58
    chtest
    -0.57
    blogspot
    -0.55
    loroethane
    -0.54
    dây
    -0.54
     utafitiHapana
    -0.54
    complexType
    -0.54
    æk
    -0.53
    InlineData
    -0.53
    POSITIVE LOGITS
    AntiForgeryToken
    0.62
     Normdatei
    0.62
    Gön
    0.53
    StructEnd
    0.53
    kloped
    0.52
     sumpay
    0.50
     estekak
    0.49
    annica
    0.48
     tartalomajánló
    0.47
     frutto
    0.47
    Activations Density 47.708%

    No Known Activations