© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3636
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people and places

    oai_token-act-pair · gemini-2.0-flash

    Technical documents

    np_max-act · gemini-2.0-flash

    say "▁"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ianum
    -0.80
    æus
    -0.77
     Theſe
    -0.75
    klart
    -0.74
    holdet
    -0.73
    grunns
    -0.72
     iconFacebook
    -0.71
     enfans
    -0.70
    gegangen
    -0.70
    ianus
    -0.69
    POSITIVE LOGITS
    riwal
    0.63
    ,
    0.57
    tonsoft
    0.57
     Normdatei
    0.55
    Filmografie
    0.55
    /*
    0.54
    extAlignment
    0.53
    ￡
    0.52
     XNUMX
    0.52
    ValueStyle
    0.51
    Activations Density 24.807%

    No Known Activations