© 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. 6230
    Prev
    Next
    INDEX
    Explanations

    words and names related to Lithuanian locations, organizations, and military units, particularly during the Holocaust

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'Y', 'P', or 'W'

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

    Lithuania or code

    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
     myſelf
    -1.30
     itſelf
    -1.29
     purpoſe
    -1.29
     pleaſure
    -1.25
     themſelves
    -1.24
    ſelves
    -1.20
     Majefty
    -1.20
    ſelf
    -1.19
     Jefus
    -1.17
     houſe
    -1.13
    POSITIVE LOGITS
     Y
    0.57
     Per
    0.54
     an
    0.54
     W
    0.51
     O
    0.49
    Y
    0.49
     P
    0.49
     Par
    0.48
     Es
    0.48
     C
    0.47
    Activations Density 0.088%

    No Known Activations