© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7120
    Prev
    Next
    INDEX
    Explanations

    instances of using words like "more," "much," "often," "too" or other intensifying words

    oai_token-act-pair · gemini-2.0-flash

    technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     propOrder
    -0.60
    encodeWith
    -0.57
     travaillons
    -0.56
    ysen
    -0.56
     Wikimedijinoj
    -0.55
     bien
    -0.53
    edance
    -0.51
    ˛
    -0.51
    nings
    -0.51
    ⎨
    -0.51
    POSITIVE LOGITS
     vPvB
    0.60
     Normdatei
    0.59
    بوابة
    0.58
    RectangleBorder
    0.57
    הערות
    0.53
     consul
    0.53
     withal
    0.52
     injective
    0.50
     متعلقه
    0.50
     EnglishChoose
    0.50
    Activations Density 6.064%

    No Known Activations