© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13137
    Prev
    Next
    INDEX
    Explanations

    references to political and religious matters, especially those related to Israel and Zionism.

    oai_token-act-pair · gemini-2.0-flash

    varied article snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Xna
    -0.70
     CreateTagHelper
    -0.63
     perfeita
    -0.62
     felizes
    -0.61
     étrangère
    -0.60
     feroit
    -0.59
     avoient
    -0.59
     orgánico
    -0.58
     retrô
    -0.58
     engraçadas
    -0.57
    POSITIVE LOGITS
     R
    0.56
     &___
    0.54
     Royal
    0.52
     O
    0.51
     Land
    0.49
     do
    0.49
     Lands
    0.49
    R
    0.48
     Do
    0.46
     Streets
    0.46
    Activations Density 4.285%

    No Known Activations