© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11892
    Prev
    Next
    INDEX
    Explanations

    what looks like mostly meaningless chunks of technical writing or business/project updates due to the amount of code-like characters among regular words

    oai_token-act-pair · gemini-2.0-flash

    words with special characters or archaic forms

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

    archaic English

    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
     «
    -1.21
     "
    -1.18
     I
    -1.17
     
    -1.17
     da
    -1.10
     A
    -1.10
     '
    -1.09
     V
    -1.07
     v
    -1.06
     E
    -1.06
    POSITIVE LOGITS
     itſelf
    2.02
     myſelf
    1.65
     Shakspeare
    1.58
     pleaſure
    1.55
     greateſt
    1.53
     Anſ
    1.52
     Reſ
    1.52
     Diſ
    1.51
     ་་
    1.49
     Majefty
    1.48
    Activations Density 4.540%

    No Known Activations