© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14310
    Prev
    Next
    INDEX
    Explanations

    words related to writing, creation, academic works and people's names

    oai_token-act-pair · gemini-2.0-flash

    accomplishments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Efq
    -1.02
    évaluateur
    -0.83
    Vidite
    -0.77
     Diſ
    -0.76
    */;
    -0.74
     oprot
    -0.74
     Anſ
    -0.72
     raiſ
    -0.69
     समीक्षक
    -0.69
     surla
    -0.68
    POSITIVE LOGITS
    iburg
    0.42
    tawesome
    0.42
    cyklopedia
    0.42
    afterEach
    0.41
     étrangères
    0.40
     servir
    0.40
    цца
    0.39
    gcm
    0.38
    Dangerous
    0.38
    zw
    0.38
    Activations Density 26.439%

    No Known Activations