© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6869
    Prev
    Next
    INDEX
    Explanations

    negative or critical statements

    oai_token-act-pair · gemini-2.0-flash

    words related to criticism or opposition

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

    Controversial or negative opinions

    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
     NavController
    -0.53
    ритори
    -0.48
     hadapan
    -0.47
     AsyncTask
    -0.47
     jurí
    -0.45
    prefixer
    -0.45
     signos
    -0.45
     vectoriales
    -0.43
     newBuilder
    -0.43
    AutoScaleMode
    -0.42
    POSITIVE LOGITS
     anti
    0.82
     haters
    0.74
     pinulongan
    0.70
     detra
    0.69
     trolls
    0.69
    fromnode
    0.66
     antis
    0.64
     autorytatywna
    0.63
     conspiracy
    0.63
     fundamental
    0.63
    Activations Density 4.343%

    No Known Activations