© 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. 14095
    Prev
    Next
    INDEX
    Explanations

    a variety of formats of text including URLs, code snippets, geographic place names, personal names, and foreign languages

    oai_token-act-pair · gemini-2.0-flash

    mixed language and code

    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
    A
    -0.37
    I
    -0.33
    S
    -0.23
    The
    -0.22
    Q
    -0.22
    For
    -0.22
    F
    -0.21
      
    -0.21
    M
    -0.20
    Get
    -0.19
    POSITIVE LOGITS
     Efq
    1.22
     Савезне
    1.12
     Monfieur
    1.10
     ―――――
    1.08
    rungsseite
    1.07
    Datuak
    1.05
    ſelf
    1.04
     Мексичка
    1.03
     MainAxisSize
    1.02
     myſelf
    1.02
    Activations Density 9.640%

    No Known Activations