© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13040
    Prev
    Next
    INDEX
    Explanations

    sentences about famous people or landmark buildings

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ResumeLayout
    -0.81
     TestBed
    -0.78
    Personendaten
    -0.75
     nahilalakip
    -0.73
     CreateTagHelper
    -0.73
    ⓧ
    -0.71
     beginnetje
    -0.69
    RegistryLite
    -0.69
     للمعارف
    -0.66
     AssemblyTitle
    -0.62
    POSITIVE LOGITS
    bootstrapcdn
    0.49
     Universitaria
    0.47
    Packard
    0.46
     obligatory
    0.44
     başına
    0.44
    harapkan
    0.43
     rudimentary
    0.43
    rentice
    0.43
     vivre
    0.42
    ContentAlignment
    0.41
    Activations Density 1.597%

    No Known Activations