© 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. 8767
    Prev
    Next
    INDEX
    Explanations

    words of comparison or cause and effect

    oai_token-act-pair · gemini-2.0-flash

    concepts related to loss

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

    loss

    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
    achella
    -0.55
    存于互联网档案馆
    -0.54
     estimés
    -0.53
    busch
    -0.48
    oweit
    -0.46
    Quoi
    -0.46
    __":
    -0.46
     énergétique
    -0.45
     mày
    -0.45
     auttaa
    -0.45
    POSITIVE LOGITS
     loss
    2.36
     Loss
    2.03
     lost
    2.02
    Loss
    1.98
    loss
    1.97
     lose
    1.91
     LOSS
    1.82
     losing
    1.78
     loses
    1.78
     losses
    1.66
    Activations Density 6.160%

    No Known Activations