© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8851
    Prev
    Next
    INDEX
    Explanations

    personal experiences or feelings, especially in potentially negative contexts

    oai_token-act-pair · gemini-2.0-flash

    self; being alone

    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
    HomeAsUpEnabled
    -0.47
     escul
    -0.45
    TagHelper
    -0.45
    phosa
    -0.45
     hänen
    -0.45
     lourd
    -0.44
     bitte
    -0.43
    的精神
    -0.43
     contacter
    -0.42
    sige
    -0.42
    POSITIVE LOGITS
     Мексичка
    0.69
    RegressionTest
    0.68
    AnimationsModule
    0.65
    ImageContext
    0.64
    المكان
    0.63
    SharedCtor
    0.59
    IsContent
    0.59
    הערות
    0.57
    ]=>
    0.57
     تضيفلها
    0.56
    Activations Density 0.282%

    No Known Activations