© 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. 12269
    Prev
    Next
    INDEX
    Explanations

    phrases that include words like "commonly", "referred", or "known"

    oai_token-act-pair · gemini-2.0-flash

    specific terms or identifiers related to devices or contextual information

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

    "also known as"

    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
     call
    -2.09
    call
    -1.93
    Call
    -1.77
     calls
    -1.77
     Call
    -1.75
     CALL
    -1.70
    CALL
    -1.63
     calling
    -1.61
     Calls
    -1.58
    calls
    -1.47
    POSITIVE LOGITS
    Tikang
    0.63
    Manbalar
    0.60
    出版年
    0.51
     مفص
    0.50
    ampu
    0.49
    BeginContext
    0.49
    seded
    0.46
    gimento
    0.46
    tvguidetime
    0.46
    hdashline
    0.46
    Activations Density 0.716%

    No Known Activations