© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13193
    Prev
    Next
    INDEX
    Explanations

    the word "up" followed by related words

    oai_token-act-pair · gemini-2.0-flash

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ressional
    -0.55
    صول
    -0.54
    atonic
    -0.54
    iric
    -0.53
    rsch
    -0.52
    ClientSize
    -0.52
     BrowserModule
    -0.52
    undred
    -0.51
    DebuggerNonUser
    -0.50
     thước
    -0.50
    POSITIVE LOGITS
    EndInit
    0.73
     disambiguazione
    0.61
     universale
    0.58
     Aprove
    0.56
     Privile
    0.56
     Administrativna
    0.55
     urma
    0.55
     séjour
    0.54
    SuccessListener
    0.54
     rubrique
    0.54
    Activations Density 1.842%

    No Known Activations