© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2152
    Prev
    Next
    INDEX
    Explanations

    words relating to military vehicles and support

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to coding or programming

    np_token-act-pair-logits · gpt-4o-mini
    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
     percentage
    -0.73
    Хьажоргаш
    -0.68
    points
    -0.63
     points
    -0.61
    RenderAtEndOf
    -0.60
    CppMethod
    -0.57
    POINTS
    -0.56
    TypedDataSet
    -0.56
    percentage
    -0.56
     nervosa
    -0.55
    POSITIVE LOGITS
     AssemblyCulture
    0.77
    KeySpec
    0.55
    AutoField
    0.53
    SequentialGroup
    0.51
     aikaa
    0.50
     صوتيه
    0.49
    NewUrlParser
    0.45
     alberi
    0.45
     cortas
    0.44
    CodedInputStream
    0.43
    Activations Density 0.305%

    No Known Activations