© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13238
    Prev
    Next
    INDEX
    Explanations

    words commonly found in addresses or locations, particularly apartments and commercial locations

    oai_token-act-pair · gemini-2.0-flash

    technical or structured phrases

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

    Indoor Locations

    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
    +:+
    -0.66
    odils
    -0.63
     Fields
    -0.61
     fields
    -0.61
     MainAxisSize
    -0.60
    ArgumentParser
    -0.58
     виправивши
    -0.58
     فريبيس
    -0.57
    AnchorStyles
    -0.57
     FIELDS
    -0.56
    POSITIVE LOGITS
    SharedModule
    0.53
    )++;
    0.49
     alti
    0.48
    ثيق
    0.47
    WriteBarrier
    0.46
     Corps
    0.46
     grit
    0.44
    eadilan
    0.43
     associées
    0.43
     element
    0.43
    Activations Density 1.805%

    No Known Activations