© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6310
    Prev
    Next
    INDEX
    Explanations

    text relating to historical wars or battles

    oai_token-act-pair · gemini-2.0-flash

    words or phrases related to battles or military events

    np_token-act-pair-logits · gpt-4o-mini

    battle locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ẤT
    -0.48
    Vidite
    -0.46
    enet
    -0.44
     мѣ
    -0.44
    eclared
    -0.43
     Cavendish
    -0.43
    يكب
    -0.43
    rals
    -0.42
    wegen
    -0.42
    MLElement
    -0.41
    POSITIVE LOGITS
    évaluateur
    0.79
     виправивши
    0.79
    ########.
    0.71
     Мексичка
    0.71
    migrationBuilder
    0.68
     HasFactory
    0.67
     resourceCulture
    0.67
     שוליים
    0.66
    fjspx
    0.65
     MotionEvent
    0.63
    Activations Density 0.595%

    No Known Activations