© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1399
    Prev
    Next
    INDEX
    Explanations

    words that are part of dialog including questions.

    oai_token-act-pair · gemini-2.0-flash

    futility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     useless
    -0.81
     pointless
    -0.78
     inuti
    -0.75
     ivelany
    -0.73
    (!__
    -0.70
    adaptiveStyles
    -0.69
     inútil
    -0.68
    resave
    -0.68
     fruitless
    -0.65
     jsPsych
    -0.63
    POSITIVE LOGITS
     sos
    0.47
    umas
    0.44
    Executives
    0.44
    delegate
    0.43
    izier
    0.43
    ั่น
    0.42
    Varint
    0.42
    biamo
    0.41
    adak
    0.40
    ensk
    0.40
    Activations Density 31.789%

    No Known Activations