© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11960
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to immune response, measurement, allergic reaction, and cells.

    oai_token-act-pair · gemini-2.0-flash

    scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    NameInMap
    -0.65
     незавершена
    -0.58
    principalColumn
    -0.57
     '\\;'
    -0.56
    expandindo
    -0.56
    SBATCH
    -0.55
     Exactos
    -0.55
     ta
    -0.55
    RegressionTest
    -0.52
     Italijani
    -0.51
    POSITIVE LOGITS
    BASEPATH
    0.58
    issauga
    0.56
     صوتيه
    0.54
     SOP
    0.53
     Aristi
    0.51
     jezt
    0.51
     Subsid
    0.50
    ellschaft
    0.49
     Whoever
    0.49
     Fils
    0.49
    Activations Density 3.119%

    No Known Activations