© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9706
    Prev
    Next
    INDEX
    Explanations

    mentions to an individual or the public

    oai_token-act-pair · gemini-2.0-flash

    himself/herself

    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
     disambiguazione
    -0.92
     مشين
    -0.68
     nahilalakip
    -0.68
     تانيه
    -0.63
     Hän
    -0.58
     himſelf
    -0.58
    tagHelper
    -0.57
     verksamhet
    -0.57
     mukana
    -0.57
    فصل
    -0.57
    POSITIVE LOGITS
    <bos>
    0.57
    BindingResult
    0.57
    processable
    0.53
     Bot
    0.53
    stdc
    0.52
    كومة
    0.52
     LUMP
    0.51
    المناصب
    0.51
    opsida
    0.51
    awtextra
    0.50
    Activations Density 2.215%

    No Known Activations