Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6115
    Prev
    Next
    INDEX
    Explanations

    words related to HP printers and printing functions

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon in computing

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

    printers and printing

    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
    setVerticalGroup
    -0.77
    #+#
    -0.66
     orgasm
    -0.60
     <=",
    -0.58
    enderror
    -0.56
    parsedMessage
    -0.56
     sputnik
    -0.55
    msgSender
    -0.54
     invokingState
    -0.53
    Discography
    -0.52
    POSITIVE LOGITS
     pleine
    0.54
    iders
    0.52
    GeneratedValue
    0.51
    bilt
    0.50
    \{\
    0.50
    ripsi
    0.48
    ImageContext
    0.48
    seite
    0.48
    ebenarnya
    0.47
     punto
    0.47
    Activations Density 1.681%

    No Known Activations