© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9991
    Prev
    Next
    INDEX
    Explanations

    strings and code snippets

    oai_token-act-pair · gemini-2.0-flash

    say 's word'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    se
    -0.97
    si
    -0.84
    so
    -0.84
    sex
    -0.81
    sed
    -0.79
    simp
    -0.79
    sa
    -0.77
    sb
    -0.77
    sy
    -0.77
    st
    -0.76
    POSITIVE LOGITS
    TRIBUN
    0.54
    +#+
    0.50
     continúas
    0.47
     pinulongan
    0.47
    MultipartFile
    0.46
    tamol
    0.46
    eqn
    0.45
    teenth
    0.45
    lccn
    0.44
     createContext
    0.44
    Activations Density 3.023%

    No Known Activations