© 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. 11699
    Prev
    Next
    INDEX
    Explanations

    Danish words and the phrase "looking forward".

    oai_token-act-pair · gemini-2.0-flash

    Directions and beginnings

    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
     Chwiliwch
    -0.83
     purpoſe
    -0.74
     fiduci
    -0.73
     Majefty
    -0.71
     Telescope
    -0.71
     oprot
    -0.69
    PhysRev
    -0.69
     itſelf
    -0.68
     pleaf
    -0.68
     photolibrary
    -0.66
    POSITIVE LOGITS
    <bos>
    0.79
     he
    0.62
     ‘
    0.62
     the
    0.58
     by
    0.55
    『
    0.55
     dem
    0.55
     to
    0.54
     '
    0.53
     him
    0.53
    Activations Density 0.178%

    No Known Activations