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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11785
    Prev
    Next
    INDEX
    Explanations

    sentences with lots of citations or references in scientific text

    oai_token-act-pair · gemini-2.0-flash

    terms related to discovery and findings

    np_token-act-pair-logits · gpt-4o-mini

    Discovery, observation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     AssemblyTitle
    -0.75
    ReusableCell
    -0.59
    TargetException
    -0.58
    PerformLayout
    -0.54
     ModelExpression
    -0.54
     seduta
    -0.53
    StoryboardSegue
    -0.52
    ագրություններ
    -0.52
    ValueStyle
    -0.50
    GetAxis
    -0.49
    POSITIVE LOGITS
     finding
    0.88
    finding
    0.76
     Finding
    0.62
    Finding
    0.60
     observation
    0.60
     Jefus
    0.59
     discovering
    0.58
     observations
    0.58
     findings
    0.57
     discovery
    0.57
    Activations Density 7.092%

    No Known Activations