© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10860
    Prev
    Next
    INDEX
    Explanations

    prepositions describing direction

    oai_token-act-pair · gemini-2.0-flash

    Movement (direction)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    LookAnd
    -0.48
    getStatusCode
    -0.45
     AssemblyProduct
    -0.43
    天王
    -0.43
    inde
    -0.43
     norm
    -0.42
    ونا
    -0.42
    бата
    -0.40
     dok
    -0.40
    漫
    -0.40
    POSITIVE LOGITS
     صوتيه
    0.91
    UrlResolution
    0.89
     poffible
    0.88
     ویکی‌پدیا
    0.87
    tagHelperRunner
    0.81
     تضيفلها
    0.80
    AddTagHelper
    0.79
    enumii
    0.78
     itſelf
    0.76
     myſelf
    0.75
    Activations Density 1.254%

    No Known Activations