© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3478
    Prev
    Next
    INDEX
    Explanations

    phrases describing things being taken seriously

    oai_token-act-pair · gemini-2.0-flash

    seriously

    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
    -0.68
     Monfieur
    -0.68
     Phry
    -0.65
     myſelf
    -0.65
     Bantu
    -0.64
     Majefty
    -0.63
     Hodgkin
    -0.63
     XNUMX
    -0.59
    ſelf
    -0.59
     Juf
    -0.59
    POSITIVE LOGITS
     take
    0.65
     виправивши
    0.61
    taken
    0.61
    take
    0.60
     Take
    0.59
     TAKE
    0.58
    aarrggbb
    0.58
     taking
    0.58
     taken
    0.58
     Taking
    0.58
    Activations Density 0.690%

    No Known Activations