© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15285
    Prev
    Next
    INDEX
    Explanations

    words about the conclusion or continuation of a period of time

    oai_token-act-pair · gemini-2.0-flash

    Time limits/expiration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Betracht
    -0.49
     
    -0.44
    <bos>
    -0.44
     Schalt
    -0.43
    vice
    -0.43
     Wait
    -0.42
    اریخ
    -0.41
     http
    -0.40
    nial
    -0.39
     (
    -0.38
    POSITIVE LOGITS
    RegressionTest
    0.84
     Shakspeare
    0.81
     surla
    0.74
    ^(@)
    0.72
    twimg
    0.69
     useAppContext
    0.68
     reCAPTCHA
    0.67
     Shaksp
    0.67
     Efq
    0.66
     Jehovah
    0.64
    Activations Density 0.726%

    No Known Activations