© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15943
    Prev
    Next
    INDEX
    Explanations

    words and phrases characteristic of argumentative or persuasive writing

    oai_token-act-pair · gemini-2.0-flash

    Problems and issues

    np_max-act-logits · gemini-2.0-flash

    issue

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     there
    -0.46
     There
    -0.45
    outon
    -0.43
    conse
    -0.42
     Cap
    -0.41
    ಮ
    -0.40
    publ
    -0.40
    必
    -0.39
     conse
    -0.39
     Th
    -0.38
    POSITIVE LOGITS
    reportWebVitals
    1.13
     Signalez
    1.01
    ValueStyle
    0.99
    awaiter
    0.97
    AndEndTag
    0.96
    enterOuterAlt
    0.94
    rungsseite
    0.93
     cherchés
    0.93
    PerformLayout
    0.93
    fjspx
    0.93
    Activations Density 33.150%

    No Known Activations