© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    the start of descriptions of related art, especially in an academic context

    oai_token-act-pair · gemini-2.0-flash

    verbs ending in -ize

    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
     defaultstate
    -0.87
    AndEndTag
    -0.87
    GEBURTSDATUM
    -0.81
    Personendaten
    -0.76
     Roskov
    -0.71
    +#+#
    -0.70
    /*---
    -0.67
    migrationBuilder
    -0.63
    AccessorTable
    -0.62
     مشين
    -0.59
    POSITIVE LOGITS
     utilizes
    0.62
     realization
    0.62
     harmonize
    0.59
     heighten
    0.58
     realize
    0.58
     maximize
    0.58
     utilizing
    0.57
     materialize
    0.57
     prioritize
    0.57
     magnify
    0.56
    Activations Density 15.842%

    No Known Activations