© 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. 15741
    Prev
    Next
    INDEX
    Explanations

    the word "birthday" and words related to business, especially when combined

    oai_token-act-pair · gemini-2.0-flash

    birthday

    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
    va
    -0.72
    ta
    -0.67
    ri
    -0.65
     pymysql
    -0.65
    ti
    -0.63
     Vallarta
    -0.62
    z
    -0.62
    an
    -0.61
    la
    -0.60
    es
    -0.60
    POSITIVE LOGITS
    ſh
    0.77
     autorytatywna
    0.76
    ratulations
    0.75
    ſtance
    0.72
    ſſer
    0.71
    ftance
    0.71
    ſion
    0.68
    windowFixed
    0.68
    öbb
    0.68
    NUMX
    0.66
    Activations Density 3.106%

    No Known Activations