© 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. 5041
    Prev
    Next
    INDEX
    Explanations

    clauses containing "which", often followed by a verb.

    oai_token-act-pair · gemini-2.0-flash

    which

    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
     and
    -0.74
     surla
    -0.71
     Means
    -0.70
     kasarigan
    -0.69
     transfieras
    -0.68
     means
    -0.67
    means
    -0.65
    FTFY
    -0.60
    Means
    -0.59
     ThemeData
    -0.57
    POSITIVE LOGITS
    providedIn
    0.57
     the
    0.55
    $_['
    0.54
     مرئيه
    0.51
    PerformLayout
    0.51
    łoś
    0.49
    quelles
    0.49
    OrBuilder
    0.48
    Segue
    0.48
    ⓧ
    0.48
    Activations Density 13.985%

    No Known Activations