© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10224
    Prev
    Next
    INDEX
    Explanations

    the word "wrong" and similar terms indicating problems

    oai_token-act-pair · gemini-2.0-flash

    wrong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     müßte
    -0.56
     ma
    -0.55
    Someday
    -0.51
     National
    -0.50
    서는
    -0.48
    timp
    -0.48
     Ma
    -0.47
     chiaro
    -0.47
    Пото
    -0.46
    فاق
    -0.46
    POSITIVE LOGITS
     '\\;'
    0.89
    Personensuche
    0.85
    endphp
    0.82
     насељу
    0.81
    //
    0.81
     censiti
    0.80
     خارجية
    0.80
     محفوظة
    0.79
     pinulongan
    0.79
     onCancelled
    0.77
    Activations Density 0.172%

    No Known Activations