© 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. 10377
    Prev
    Next
    INDEX
    Explanations

    text describing the process of flaming stone, especially granite

    oai_token-act-pair · gemini-2.0-flash

    Material surface properties

    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
    Personensuche
    -0.66
     BorderRadius
    -0.64
     GenerationType
    -0.62
    XmlAccessorType
    -0.62
    BeginContext
    -0.56
     Vikipedi
    -0.55
     onOptions
    -0.54
     kasarigan
    -0.53
    TagHelpers
    -0.53
    
    -0.52
    POSITIVE LOGITS
    lorette
    0.55
    Bioaccumulative
    0.55
    acyj
    0.55
     contraction
    0.53
     interesar
    0.51
    τρι
    0.51
    AutoScaleMode
    0.51
     hard
    0.50
    findpost
    0.50
    soft
    0.49
    Activations Density 1.625%

    No Known Activations