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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10864
    Prev
    Next
    INDEX
    Explanations

    language around increases and decreases

    oai_token-act-pair · gemini-2.0-flash

    increase or decrease

    np_max-act · 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
    Datuak
    -0.75
     متعلقه
    -0.61
     ISNI
    -0.60
     viewDidLoad
    -0.60
     CiNii
    -0.58
    EnableWeb
    -0.58
     الحره
    -0.57
     الدولى
    -0.56
    esez
    -0.55
    VersionUID
    -0.54
    POSITIVE LOGITS
     Kraw
    0.49
    SOUNDBITE
    0.45
     незавершена
    0.44
    enares
    0.44
     Jura
    0.43
    Stmt
    0.42
    MINUTES
    0.42
    ActionCreators
    0.41
    SuppressMessage
    0.41
     !}
    0.41
    Activations Density 0.873%

    No Known Activations