© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9229
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to being isolated or alone

    oai_token-act-pair · gemini-2.0-flash

    the concept of being alone

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

    alone

    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
     &___
    -0.59
    
    -0.58
    Rüyada
    -0.58
    MethodManager
    -0.58
    Климат
    -0.57
    onViewCreated
    -0.56
    بوابة
    -0.56
    rawDesc
    -0.54
    ListItemIcon
    -0.53
    GHIJKLM
    -0.52
    POSITIVE LOGITS
     alone
    2.47
     Alone
    2.06
    alone
    1.94
     ALONE
    1.88
    Alone
    1.73
     alene
    1.48
     allein
    1.31
     seul
    1.30
     alleine
    1.25
     solo
    1.19
    Activations Density 2.241%

    No Known Activations