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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13628
    Prev
    Next
    INDEX
    Explanations

    the verb 'fall' or 'fell', sometimes in conjunction with the preposition 'in' or 'into'

    oai_token-act-pair · gemini-2.0-flash

    fall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    kloped
    -0.62
     bezeichneter
    -0.59
    AsUp
    -0.58
    JvmStatic
    -0.54
    stdafx
    -0.54
     Wicidata
    -0.53
    OGND
    -0.52
    rungsseite
    -0.52
    ーブル
    -0.52
    🏽
    -0.52
    POSITIVE LOGITS
     asleep
    0.56
     victim
    0.55
    бята
    0.53
    Worse
    0.52
     victime
    0.49
     pubb
    0.47
     जाए
    0.46
    ffre
    0.46
    pegno
    0.45
    helia
    0.45
    Activations Density 0.586%

    No Known Activations