© 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. 5076
    Prev
    Next
    INDEX
    Explanations

    future tense prediction of events/actions.

    oai_token-act-pair · gemini-2.0-flash

    keep

    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
    Continuing
    -0.69
     Continuing
    -0.67
     ujednoznacz
    -0.66
     melanjutkan
    -0.65
    httphttps
    -0.61
    continuing
    -0.61
    ViewFeatures
    -0.60
     continuing
    -0.56
     poursuivre
    -0.56
    rrggbb
    -0.56
    POSITIVE LOGITS
     keep
    2.41
     kept
    2.23
     keeps
    2.22
    keep
    2.19
     Keep
    2.17
    Keep
    2.14
     keeping
    2.08
     KEEP
    2.06
    keeps
    2.02
    kept
    1.99
    Activations Density 6.688%

    No Known Activations