© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10522
    Prev
    Next
    INDEX
    Explanations

    text describing the chemical properties of ions and liquids

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ::_('
    -0.54
     atve
    -0.53
    (&:
    -0.51
     становника
    -0.49
    uração
    -0.49
    สน
    -0.45
     fupp
    -0.45
    Му
    -0.45
     Acho
    -0.44
     Mitte
    -0.44
    POSITIVE LOGITS
     Савезне
    0.73
    tvguidetime
    0.73
    帖最后由
    0.63
    SourceChecksum
    0.63
    SequentialGroup
    0.63
    Kjelder
    0.61
    Véxase
    0.60
     utafitiHapana
    0.58
    ThroughAttribute
    0.57
     ویکی‌پدی
    0.57
    Activations Density 0.939%

    No Known Activations