© 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. 5297
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to speed and change

    oai_token-act-pair · gemini-2.0-flash

    technical terms or coding-related concepts

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

    fast

    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
    twimg
    -0.71
    +#+#
    -0.58
    migrationBuilder
    -0.56
     ligiloj
    -0.54
    帖最后由
    -0.49
     {:.
    -0.48
    getJSONObject
    -0.46
    ".$
    -0.46
     board
    -0.45
     Board
    -0.45
    POSITIVE LOGITS
    AnchorStyles
    0.59
    ImageContext
    0.58
     aérienne
    0.56
    erals
    0.56
     useRouter
    0.55
    rawDesc
    0.55
    parsedMessage
    0.55
    StoryboardSegue
    0.54
     întâ
    0.54
     carab
    0.53
    Activations Density 5.307%

    No Known Activations