© 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. 5581
    Prev
    Next
    INDEX
    Explanations

    long alphanumeric strings

    oai_token-act-pair · gemini-2.0-flash

    Random alphanumeric strings

    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
     -
    -2.09
    –
    -1.95
    --
    -1.77
    —
    -1.52
    "-
    -1.51
     –
    -1.50
    ”-
    -1.50
    }-
    -1.50
    -“
    -1.47
    )-
    -1.46
    POSITIVE LOGITS
     referenties
    0.68
     CreateTagHelper
    0.67
    \{\\
    0.64
     Мексичка
    0.61
    WEBPACK
    0.60
    IonicModule
    0.57
    hasOwnProperty
    0.55
    〝
    0.55
     stanovnika
    0.54
    VersionUID
    0.52
    Activations Density 9.978%

    No Known Activations