© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11452
    Prev
    Next
    INDEX
    Explanations

    words related to beaches, trails, bodies of water and outdoor activities

    oai_token-act-pair · gemini-2.0-flash

    beach or mountain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     مشين
    -0.83
    SourceChecksum
    -0.77
     وتسجيلات
    -0.75
     OFDb
    -0.69
     entanto
    -0.66
     continúas
    -0.64
     gewor
    -0.64
    بوابة
    -0.64
    __':
    -0.63
     légende
    -0.62
    POSITIVE LOGITS
    top
    0.49
     kayaks
    0.46
     fork
    0.44
    y
    0.43
    AfterViewInit
    0.43
    root
    0.42
    agaimana
    0.41
    ziem
    0.40
     framed
    0.40
     meets
    0.39
    Activations Density 2.917%

    No Known Activations