© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7676
    Prev
    Next
    INDEX
    Explanations

    the word "inches"

    oai_token-act-pair · gemini-2.0-flash

    inches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     menangis
    -0.64
     Köz
    -0.63
     tambin
    -0.63
     Grand
    -0.60
    DockStyle
    -0.59
    Fordítás
    -0.59
     kasarigan
    -0.58
    ustice
    -0.57
     mengal
    -0.56
     penghargaan
    -0.56
    POSITIVE LOGITS
     Baillargeon
    0.70
     photolibrary
    0.69
     Klan
    0.68
     satan
    0.65
    Abit
    0.64
     Résultat
    0.64
     Neander
    0.64
     Uff
    0.63
     Thebes
    0.63
     bezeichneter
    0.63
    Activations Density 1.972%

    No Known Activations