© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10757
    Prev
    Next
    INDEX
    Explanations

    common words, especially propositions, conjunctions, pronouns, and helping verbs

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    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
     these
    -2.72
    these
    -2.58
    this
    -2.50
     this
    -2.42
    These
    -2.34
     These
    -2.33
     THESE
    -2.08
     This
    -1.99
    This
    -1.97
     THIS
    -1.90
    POSITIVE LOGITS
    GraphicsUnit
    0.73
    TagMode
    0.73
    SequentialGroup
    0.58
    PYX
    0.58
     defaultstate
    0.55
     Roskov
    0.54
    Hauptartikel
    0.54
    Rhestr
    0.54
    inheritDoc
    0.53
     Normdatei
    0.52
    Activations Density 13.218%

    No Known Activations