© 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. 7866
    Prev
    Next
    INDEX
    Explanations

    words, prefixes, and suffixes in Croatian related to computer accounts and email addresses

    oai_token-act-pair · gemini-2.0-flash

    rač

    np_max-act · gemini-2.0-flash

    ▁rač

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     picioare
    -3.22
     feroit
    -3.19
     avoient
    -3.16
     auroit
    -3.09
     étoient
    -2.92
     varandra
    -2.89
     fermés
    -2.83
     mukana
    -2.81
     aikaa
    -2.80
     pouvoit
    -2.78
    POSITIVE LOGITS
     ver
    1.31
     ter
    1.20
     di
    1.18
     tem
    1.18
     op
    1.17
     der
    1.17
     tr
    1.17
     fra
    1.16
     har
    1.14
     om
    1.13
    Activations Density 1.862%

    No Known Activations