© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15154
    Prev
    Next
    INDEX
    Explanations

    expressions of regret or apology

    oai_token-act-pair · gemini-2.0-flash

    Mistakes and regret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    <?
    -0.80
    Aholisi
    -0.72
     Wiktionnaire
    -0.71
     NSCoder
    -0.71
    richTextPanel
    -0.70
    rungsseite
    -0.69
    HasAnnotation
    -0.67
    AddTagHelper
    -0.67
    Datuak
    -0.67
    verwijspagina
    -0.66
    POSITIVE LOGITS
    Mog
    0.40
    Oso
    0.39
     gant
    0.39
    prod
    0.38
     Parte
    0.38
    влению
    0.38
    área
    0.37
    작
    0.37
     Oso
    0.36
    urlar
    0.36
    Activations Density 2.773%

    No Known Activations