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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9656
    Prev
    Next
    INDEX
    Explanations

    opinions and arguments

    oai_token-act-pair · gemini-2.0-flash

    written or spoken

    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
     NSCoder
    -0.67
     мәгълү
    -0.65
    Населення
    -0.63
    COUVER
    -0.61
    MigrationBuilder
    -0.61
     CAKE
    -0.60
    principalTable
    -0.59
    yntaxException
    -0.58
     createState
    -0.58
    putan
    -0.58
    POSITIVE LOGITS
     printed
    0.70
     delivered
    0.67
     written
    0.65
     taken
    0.64
     given
    0.60
     applied
    0.56
     uttered
    0.55
     read
    0.55
     exchanged
    0.55
     imprinted
    0.53
    Activations Density 9.846%

    No Known Activations