© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11348
    Prev
    Next
    INDEX
    Explanations

    the word "kick" or "Kick" possibly followed by "starter", "things", or "-start"

    oai_token-act-pair · gemini-2.0-flash

    the keyword 'kick'

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

    kick

    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
    VIAF
    -0.64
     relâche
    -0.57
     يتيمه
    -0.57
     føl
    -0.54
     محفوظة
    -0.53
    InputBorder
    -0.53
     Covering
    -0.52
    addGap
    -0.52
    ContentAlignment
    -0.51
    mitter
    -0.50
    POSITIVE LOGITS
    Билгалдахарш
    0.63
    mybatisplus
    0.57
    verwijspagina
    0.57
    مصادر
    0.53
     &___
    0.52
    
    0.51
    webElementXpaths
    0.50
     survival
    0.50
     initComponents
    0.50
    tagHelperRunner
    0.49
    Activations Density 0.531%

    No Known Activations