© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10283
    Prev
    Next
    INDEX
    Explanations

    the word "for" or time-related words

    oai_token-act-pair · gemini-2.0-flash

    who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nahilalakip
    -1.39
    writeFieldEnd
    -1.18
    ArrowToggle
    -1.15
    IndentedString
    -1.11
    IVEREF
    -1.09
     OFDb
    -1.09
     AssemblyCulture
    -1.06
    WebVitals
    -1.06
    ########.
    -1.03
     snippetHide
    -1.00
    POSITIVE LOGITS
     who
    3.13
    who
    2.50
     Who
    2.16
    Who
    2.14
     quien
    1.67
     quién
    1.51
    WHO
    1.50
    Quién
    1.47
     whom
    1.44
     WHO
    1.44
    Activations Density 2.463%

    No Known Activations