© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12858
    Prev
    Next
    INDEX
    Explanations

    the word "whatever"

    oai_token-act-pair · gemini-2.0-flash

    whatever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     whatever
    -2.63
    Whatever
    -2.38
    whatever
    -2.36
     Whatever
    -2.31
     whichever
    -1.91
    hichever
    -1.60
     whoever
    -1.58
     whome
    -1.53
     wherever
    -1.38
    atever
    -1.28
    POSITIVE LOGITS
     Macht
    0.47
    Filmografie
    0.46
    ளி
    0.46
    HomeAsUpEnabled
    0.46
    Revenir
    0.46
    Sucesor
    0.44
    WebControls
    0.44
     son
    0.44
    Filmographie
    0.44
    డు
    0.43
    Activations Density 2.782%

    No Known Activations