© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8577
    Prev
    Next
    INDEX
    Explanations

    words related to biology, zoology or medicine

    oai_token-act-pair · gemini-2.0-flash

    animals and species

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     intptr
    -0.61
    MigrationBuilder
    -0.58
    WindowConstants
    -0.56
     مشين
    -0.56
     StatelessWidget
    -0.55
    Personendaten
    -0.54
    ChildScrollView
    -0.54
    guien
    -0.53
    Neues
    -0.53
     tartalomajánló
    -0.53
    POSITIVE LOGITS
     defaultstate
    0.59
    fromCharCode
    0.57
    ürt
    0.53
    Sti
    0.52
    Fandom
    0.52
    łasz
    0.52
     tele
    0.51
     télé
    0.48
    Tele
    0.47
    stick
    0.46
    Activations Density 4.916%

    No Known Activations