© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11768
    Prev
    Next
    INDEX
    Explanations

    German language text

    oai_token-act-pair · gemini-2.0-flash

    lich

    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
    SerializedSize
    -0.59
     ModelExpression
    -0.56
    ={`/
    -0.54
     Wikimedijinoj
    -0.53
     الرياضيه
    -0.53
    يميديا
    -0.53
     Савезне
    -0.52
    devším
    -0.51
    prache
    -0.50
    เภ
    -0.49
    POSITIVE LOGITS
    SourceChecksum
    0.70
    ivar
    0.53
     поду
    0.51
    documentElement
    0.50
    帖最后由
    0.49
    Viitteet
    0.49
    PropertyGroup
    0.48
     veu
    0.48
    tifiable
    0.48
    RLock
    0.46
    Activations Density 13.200%

    No Known Activations