© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10339
    Prev
    Next
    INDEX
    Explanations

    code snippets of russian text that include punctuation and question/answer structures

    oai_token-act-pair · gemini-2.0-flash

    technical coding terms or symbols

    np_token-act-pair-logits · gpt-4o-mini
    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
     quæ
    -0.58
     venons
    -0.54
     Theſe
    -0.53
     MNRAS
    -0.50
     ul
    -0.49
     themſelves
    -0.49
     ſy
    -0.47
    jgl
    -0.47
    号線
    -0.46
     Thirdly
    -0.46
    POSITIVE LOGITS
     يتيمه
    0.87
    protoimpl
    0.67
     '\\;'
    0.66
    Jeografia
    0.64
    ValueStyle
    0.58
    SequentialGroup
    0.57
    izr
    0.56
    XmlAccessorType
    0.54
     Ре
    0.53
     NSCoder
    0.52
    Activations Density 0.478%

    No Known Activations