© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11425
    Prev
    Next
    INDEX
    Explanations

    information about parentage

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.75
    MemoryWarning
    -0.59
     &___
    -0.57
    Hozzáférés
    -0.54
    ற்ற
    -0.53
    createServer
    -0.51
    +:+
    -0.47
    ourge
    -0.44
     Dapper
    -0.44
    ReusableCell
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    0.70
    mybatisplus
    0.68
     électroniques
    0.60
     незавершена
    0.58
    ArgumentParser
    0.57
     mijne
    0.57
    OGND
    0.56
     Roskov
    0.55
    webElementXpaths
    0.55
    onAttach
    0.55
    Activations Density 3.584%

    No Known Activations