© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8020
    Prev
    Next
    INDEX
    Explanations

    varied, but generally proper nouns and other terminology related to people's lives, particularly when multiple occur in a short span.

    oai_token-act-pair · gemini-2.0-flash

    Living/Residence

    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
     living
    -3.03
    living
    -2.77
     Living
    -2.73
    Living
    -2.73
     live
    -2.67
    live
    -2.45
     LIVING
    -2.45
    Live
    -2.39
     lived
    -2.38
     Live
    -2.38
    POSITIVE LOGITS
     DBNull
    0.57
     مرئيه
    0.57
    leau
    0.46
    存于互联网档案馆
    0.46
    ði
    0.45
    enga
    0.45
    ANGA
    0.44
    cyklopedia
    0.44
     OMITTED
    0.44
    SPARENT
    0.43
    Activations Density 3.207%

    No Known Activations