© 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. 12567
    Prev
    Next
    INDEX
    Explanations

    double and single quotes

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    np_max-act · gemini-2.0-flash
    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
     Efq
    -1.59
     Jefus
    -1.34
     ―――――
    -1.30
     Majefty
    -1.29
     itſelf
    -1.28
     myſelf
    -1.27
     Theſe
    -1.26
     Anſ
    -1.26
     ſtate
    -1.25
    ſelves
    -1.24
    POSITIVE LOGITS
    ("
    1.25
    ('
    1.22
    ="
    1.03
    ['
    0.86
    ='
    0.83
    ["
    0.83
    '
    0.79
    ','
    0.73
    >("
    0.72
    ↵↵
    0.71
    Activations Density 0.393%

    No Known Activations