© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10181
    Prev
    Next
    INDEX
    Explanations

    the lower-case letter i, often followed by a period (likely part of the abbreviation "i.e.")

    oai_token-act-pair · gemini-2.0-flash

    i

    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
    ANTLR
    -0.73
     i
    -0.67
     Normdatei
    -0.63
    httphttps
    -0.60
    LookAnd
    -0.56
     [
    -0.55
    iem
    -0.53
    ConstraintMaker
    -0.53
     I
    -0.52
    verwijspagina
    -0.52
    POSITIVE LOGITS
    RegressionTest
    0.65
     varandra
    0.59
    ParallelGroup
    0.57
    !")
    
    0.57
     couverte
    0.57
     anún
    0.56
    rambled
    0.55
    DoubleQuotes
    0.55
     niedersachsen
    0.54
     Theſe
    0.54
    Activations Density 1.366%

    No Known Activations