© 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. 10161
    Prev
    Next
    INDEX
    Explanations

    text semantically related to the start of a corporate press release about a conference and a webcast.

    oai_token-act-pair · gemini-2.0-flash

    investor relations information

    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
    AttributeSet
    -0.60
     bande
    -0.55
    ---|
    -0.53
     Hof
    -0.50
     JpaRepository
    -0.50
    arXiv
    -0.50
     os
    -0.49
     oeuvres
    -0.49
    ToolStrip
    -0.48
     травня
    -0.48
    POSITIVE LOGITS
     snippetHide
    0.67
    +:+
    0.65
    BeginContext
    0.62
    Personendaten
    0.62
     ComVisible
    0.59
     nakalista
    0.57
    MigrationBuilder
    0.56
    asyarakat
    0.55
     Pergamon
    0.55
     Teig
    0.54
    Activations Density 1.115%

    No Known Activations