© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3062
    Prev
    Next
    INDEX
    Explanations

    terms related to legal agreements and the transfer of property.

    oai_token-act-pair · gemini-2.0-flash

    words related to exercise or functioning

    np_token-act-pair-logits · gpt-4o-mini

    contracts and property

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Drafting
    -0.52
    },(
    -0.50
     bisous
    -0.45
     ambi
    -0.44
    Père
    -0.44
     Containing
    -0.44
    Zalety
    -0.44
     Desk
    -0.43
     Blaise
    -0.43
     Embedding
    -0.43
    POSITIVE LOGITS
     exercise
    0.82
     EXERC
    0.75
     Exercise
    0.73
    Exercise
    0.71
     pinulongan
    0.70
    exercise
    0.68
    RegressionTest
    0.66
    دانشنامهٔ
    0.66
    __*/
    0.66
     exercising
    0.65
    Activations Density 2.580%

    No Known Activations