© 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. 13148
    Prev
    Next
    INDEX
    Explanations

    capital letters embedded in words

    oai_token-act-pair · gemini-2.0-flash

    unusual or malformed token sequences

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

    Code/configurations

    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
    AndEndTag
    -0.73
    WaitGroup
    -0.47
    日閲覧
    -0.44
    ביוגרפיה
    -0.43
    كري
    -0.42
     disparu
    -0.41
    DockStyle
    -0.41
     архив
    -0.39
    AddHtmlAttribute
    -0.38
    GroupLayout
    -0.38
    POSITIVE LOGITS
    UnknownFields
    0.73
     Majefty
    0.61
     للمعارف
    0.59
    StoreMessageInfo
    0.59
    ))));
    0.59
     Jefus
    0.59
    */;
    0.58
    )))));
    0.58
     fhew
    0.58
     hasNext
    0.57
    Activations Density 0.803%

    No Known Activations