© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6575
    Prev
    Next
    INDEX
    Explanations

    instances of "has" or "have" followed/preceded by a verb

    oai_token-act-pair · gemini-2.0-flash

    increase and decrease

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     utafitiHapana
    -0.80
    Obrázky
    -0.75
    Демографія
    -0.65
    Numerade
    -0.62
    TabIndex
    -0.59
     typelib
    -0.57
    PutMapping
    -0.57
    createComponent
    -0.56
    Datuak
    -0.55
     dado
    -0.53
    POSITIVE LOGITS
    IGraphics
    0.59
    findpost
    0.54
    AsyncTask
    0.50
    Autoritní
    0.49
    ListActivity
    0.43
    MENAFN
    0.42
    solr
    0.42
    Jenis
    0.42
    postDelayed
    0.41
     GW
    0.40
    Activations Density 3.198%

    No Known Activations