© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11234
    Prev
    Next
    INDEX
    Explanations

    text from academic papers, including assumptions, conditions, sections, and rules

    oai_token-act-pair · gemini-2.0-flash

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     متعلقه
    -0.68
    存于互联网档案馆
    -0.67
    expandindo
    -0.63
    UTERS
    -0.62
    تقاوى
    -0.60
    DllImport
    -0.60
    PreferredItem
    -0.56
    inSlope
    -0.53
    tagHelperRunner
    -0.53
     transfieras
    -0.53
    POSITIVE LOGITS
     state
    3.52
    state
    3.14
     states
    2.95
     State
    2.70
    State
    2.64
     STATE
    2.64
    states
    2.61
    STATE
    2.52
     States
    2.23
     estado
    2.23
    Activations Density 7.230%

    No Known Activations