© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6125
    Prev
    Next
    INDEX
    Explanations

    uses of "I" and "you" in a conversation.

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating confusion or questioning

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

    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_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
     通販
    -0.67
    BeginContext
    -0.65
    enderror
    -0.59
     intptr
    -0.57
     chofe
    -0.55
    LLocation
    -0.53
    InputBorder
    -0.52
     äls
    -0.52
     وتسجيلات
    -0.52
     prisonniers
    -0.51
    POSITIVE LOGITS
     فريبيس
    0.57
    KURZBESCHREIBUNG
    0.54
     '{@
    0.53
     lenker
    0.50
     دیکھیے
    0.50
    θα
    0.47
     rax
    0.47
     onOptions
    0.47
    SourceChecksum
    0.47
    migrationBuilder
    0.46
    Activations Density 0.309%

    No Known Activations