© 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. 12469
    Prev
    Next
    INDEX
    Explanations

    transitions in sentences, lists or phrases delimited by commas, periods, and conjunctions, in both English and Chinese

    oai_token-act-pair · gemini-2.0-flash

    punctuation and formatting patterns

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

    commas

    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
    ,
    -0.75
     which
    -0.57
     She
    -0.57
    ipedi
    -0.47
     néz
    -0.45
    iae
    -0.43
    deleteUser
    -0.42
     or
    -0.42
     who
    -0.41
     I
    -0.41
    POSITIVE LOGITS
     Audiodateien
    0.71
    theless
    0.69
     Majefty
    0.68
    !')
    0.67
    !")
    
    0.66
    ValueStyle
    0.66
    !")
    0.65
     doInBackground
    0.63
     Shakspeare
    0.63
    )"),
    0.62
    Activations Density 0.589%

    No Known Activations