© 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. 4150
    Prev
    Next
    INDEX
    Explanations

    the word "alike"

    oai_token-act-pair · gemini-2.0-flash

    alike

    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
     houſe
    -0.91
     Conſ
    -0.89
     Perſ
    -0.85
     ſtate
    -0.84
     itſelf
    -0.83
     Inſ
    -0.82
     ſever
    -0.82
     Jefus
    -0.81
     ſuch
    -0.80
     againſt
    -0.79
    POSITIVE LOGITS
     виправивши
    0.86
    upol
    0.85
    раздо
    0.82
     Meksiku
    0.82
     <<<<<<<<<<<<<<
    0.78
    PreferredItem
    0.77
     للاسماء
    0.76
    CopyWith
    0.73
    uxxxx
    0.72
    "}},
    0.72
    Activations Density 0.859%

    No Known Activations