© 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. 3262
    Prev
    Next
    INDEX
    Explanations

    military themed descriptive language that evokes images from stories about combat

    oai_token-act-pair · gemini-2.0-flash

    military contexts

    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
     onPostExecute
    -0.60
     armées
    -0.60
     saites
    -0.57
    gonic
    -0.56
    Kjelder
    -0.55
     vectorielles
    -0.55
    достатки
    -0.53
     мәкал
    -0.51
    بوابة
    -0.50
     définiti
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.63
    WireFormatLite
    0.54
     APL
    0.54
     AspNetCore
    0.53
    Naissance
    0.52
    aung
    0.52
     Mand
    0.51
     clavic
    0.50
    DJANGO
    0.50
    CppMethod
    0.49
    Activations Density 1.262%

    No Known Activations