© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9432
    Prev
    Next
    INDEX
    Explanations

    words relating to legal obligations and agreements, and also seems to activate when seeing 'ee' at the end of a word

    oai_token-act-pair · gemini-2.0-flash

    legal/interview texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    kách
    -0.53
    ổng
    -0.48
    TagHelpers
    -0.48
     venomous
    -0.46
     passionate
    -0.46
    legte
    -0.46
    pente
    -0.45
     papan
    -0.45
    Diwedd
    -0.44
     continents
    -0.44
    POSITIVE LOGITS
    ագրություններ
    0.82
    يكب
    0.80
    Jîn
    0.77
    Референце
    0.73
    ]")]
    0.69
    횟
    0.65
     متعلقه
    0.64
    Становништво
    0.64
    MLLoader
    0.63
    Referanser
    0.63
    Activations Density 2.004%

    No Known Activations