© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10550
    Prev
    Next
    INDEX
    Explanations

    the word "and" preceded or followed by mechanical or physical procedures

    oai_token-act-pair · gemini-2.0-flash

    prepositions indicating movement or direction

    np_token-act-pair-logits · gpt-4o-mini

    spatial prepositions

    np_max-act-logits · gemini-2.0-flash
    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
    GraphicsUnit
    -0.64
     estekak
    -0.57
    帖最后由
    -0.55
     giustizia
    -0.53
     marinho
    -0.51
     puissiez
    -0.51
     JADX
    -0.51
    WireFormatLite
    -0.51
    uable
    -0.49
     externes
    -0.49
    POSITIVE LOGITS
     into
    1.39
     past
    1.34
     down
    1.31
     through
    1.26
     across
    1.18
     back
    1.14
     out
    1.14
     forward
    1.11
     up
    1.09
     onto
    1.06
    Activations Density 2.858%

    No Known Activations