© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11521
    Prev
    Next
    INDEX
    Explanations

    words starting with "mis-", often with additional activation for nearby suffixes and prefixes

    oai_token-act-pair · gemini-2.0-flash

    mis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    TextSpan
    -0.58
    marginHorizontal
    -0.55
     referrerpolicy
    -0.49
     Bogen
    -0.47
    lista
    -0.45
    paddingVertical
    -0.44
     parts
    -0.43
    UI
    -0.43
     box
    -0.43
    alist
    -0.43
    POSITIVE LOGITS
    Tikang
    0.67
     beginnetje
    0.63
    ContentAsync
    0.61
    الإنجليزية
    0.59
    EndContext
    0.59
     مرئيه
    0.57
     للاسماء
    0.56
    %)$
    0.55
    haltens
    0.55
     forState
    0.54
    Activations Density 0.559%

    No Known Activations