© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5752
    Prev
    Next
    INDEX
    Explanations

    references to internal sensations and emotions, often in conjunction with the word "a".

    oai_token-act-pair · gemini-2.0-flash

    uncomfortable sudden sensation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    AndEndTag
    -0.81
    AddTagHelper
    -0.79
    /*
    -0.71
     lenker
    -0.70
    rungsseite
    -0.67
    webElementXpaths
    -0.63
    tvguidetime
    -0.63
     Audiodateien
    -0.63
    DebuggerNonUser
    -0.60
     متعلقه
    -0.60
    POSITIVE LOGITS
     flicker
    0.56
     splitting
    0.51
     pang
    0.50
     tw
    0.50
     EdgeInsets
    0.48
     shiver
    0.46
    richTextPanel
    0.46
     flash
    0.45
     knot
    0.44
     gna
    0.43
    Activations Density 1.227%

    No Known Activations