© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13317
    Prev
    Next
    INDEX
    Explanations

    text related to advertising technology with a focus on video and data

    oai_token-act-pair · gemini-2.0-flash

    foreign language terms

    np_token-act-pair-logits · gpt-4o-mini

    Advertising/Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     BoxFit
    -0.94
    tableFuture
    -0.88
     препратки
    -0.87
    FunctionFlags
    -0.82
    .*")]
    -0.82
     незавершена
    -0.81
    ChildScrollView
    -0.80
     дописавши
    -0.77
     Roskov
    -0.71
    достатки
    -0.71
    POSITIVE LOGITS
    րջ
    0.45
     ouest
    0.44
    Companion
    0.43
    壁
    0.42
     régionales
    0.42
    žite
    0.42
    דיה
    0.41
     croix
    0.41
    gin
    0.41
     preferencias
    0.40
    Activations Density 1.308%

    No Known Activations