© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1390
    Prev
    Next
    INDEX
    Explanations

    words and phrases about cycles and mythology

    oai_token-act-pair · gemini-2.0-flash

    cosm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    CPtr
    -0.96
    MigrationBuilder
    -0.85
    ConstraintMaker
    -0.84
    DockStyle
    -0.81
     ddelweddau
    -0.78
    enumi
    -0.75
    NewUrlParser
    -0.75
    AsUp
    -0.74
    ticides
    -0.74
    MessageTagHelper
    -0.71
    POSITIVE LOGITS
     ogóle
    0.51
     allmän
    0.47
     propriedade
    0.45
     argint
    0.44
    ちな
    0.44
     estrictamente
    0.44
    枭
    0.43
     actuelles
    0.42
     indeed
    0.42
    nande
    0.42
    Activations Density 1.320%

    No Known Activations