© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11502
    Prev
    Next
    INDEX
    Explanations

    words related to past events, changes, or processes

    oai_token-act-pair · gemini-2.0-flash

    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_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
    ’
    -0.62
    '
    -0.57
     of
    -0.55
    UnusedPrivate
    -0.54
    zs
    -0.52
    als
    -0.51
    kinds
    -0.50
     tartalomajánló
    -0.49
    TLE
    -0.48
     هيا
    -0.47
    POSITIVE LOGITS
    TagMode
    0.61
    raded
    0.55
    })*/
    0.54
    rrggbb
    0.52
    RunWith
    0.51
    phazard
    0.49
    EndGlobalSection
    0.48
    GeneratedCode
    0.47
     MotionEvent
    0.47
    //</
    0.47
    Activations Density 35.479%

    No Known Activations