© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10657
    Prev
    Next
    INDEX
    Explanations

    the word "so" in a larger context of german language

    oai_token-act-pair · gemini-2.0-flash

    German language and politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     незавершена
    -0.74
    GraphicsUnit
    -0.69
    iNdEx
    -0.65
    /**
    -0.64
    Personensuche
    -0.64
    jspx
    -0.64
    JsonPropertyName
    -0.62
    UnknownFields
    -0.62
    UnitTesting
    -0.62
     defaultstate
    -0.61
    POSITIVE LOGITS
    ⓧ
    0.45
    reiben
    0.45
    awar
    0.43
    ha
    0.43
    Reg
    0.42
    erba
    0.42
     зав
    0.42
    riu
    0.42
     els
    0.42
     er
    0.42
    Activations Density 0.519%

    No Known Activations