© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5529
    Prev
    Next
    INDEX
    Explanations

    mentions of attempts and success

    oai_token-act-pair · gemini-2.0-flash

    attempt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     attempt
    -2.47
     attempts
    -2.22
     attempted
    -2.17
    attempt
    -2.09
    <bos>
    -2.08
     Attempt
    -1.97
     attempting
    -1.97
    Attempt
    -1.83
    attempts
    -1.77
     Attempts
    -1.75
    POSITIVE LOGITS
    ########.
    0.69
     linkovi
    0.63
    zarchiwizowane
    0.62
    UnusedPrivate
    0.59
    IntoConstraints
    0.58
     dancer
    0.58
    Baca
    0.58
     Tenga
    0.57
    ãng
    0.56
    :✨
    0.56
    Activations Density 1.388%

    No Known Activations