© 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. 14573
    Prev
    Next
    INDEX
    Explanations

    references to tables and figures, and arrangements of people and objects

    oai_token-act-pair · gemini-2.0-flash

    words related to tables and seating arrangements

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

    refers to tables

    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
    hin
    -0.47
    LikeLiked
    -0.36
    ʚ
    -0.35
     dom
    -0.35
     seventy
    -0.35
     Vol
    -0.34
    ссора
    -0.34
     chains
    -0.34
     ax
    -0.34
    hasMoreElements
    -0.34
    POSITIVE LOGITS
     صوتيه
    0.94
    richTextPanel
    0.94
     <=",
    0.92
    ThroughAttribute
    0.87
     Signalez
    0.85
     Wicidata
    0.79
     utafitiHapana
    0.79
     мәкал
    0.79
     esternos
    0.79
     שוליים
    0.78
    Activations Density 1.545%

    No Known Activations