© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12818
    Prev
    Next
    INDEX
    Explanations

    a grab bag of words not strongly related to each other

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act · gemini-2.0-flash

    say "▁" words Method used: 2 — tokens mostly start with ▁ — say "▁" words

    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
    falgar
    -0.69
     per
    -0.64
     di
    -0.60
     van
    -0.60
    vermögen
    -0.59
     ca
    -0.57
     fe
    -0.56
     rest
    -0.56
    phazard
    -0.55
     et
    -0.54
    POSITIVE LOGITS
     purpoſe
    1.13
     ſever
    1.10
    <bos>
    0.99
     Monfieur
    0.99
     Anſ
    0.95
     ſta
    0.93
     ſeveral
    0.92
     pleaſure
    0.92
     ſtate
    0.91
     ſche
    0.90
    Activations Density 0.545%

    No Known Activations