© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14199
    Prev
    Next
    INDEX
    Explanations

    the word "something" and titles of publications

    oai_token-act-pair · gemini-2.0-flash

    something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     something
    -1.98
    something
    -1.76
    Something
    -1.75
     Something
    -1.61
    <bos>
    -1.44
     SOMETHING
    -1.34
     qualcosa
    -1.16
     somethin
    -1.11
     sesuatu
    -0.99
     iets
    -0.90
    POSITIVE LOGITS
    ftagPool
    0.82
    لسط
    0.64
    jspx
    0.60
     صوتيه
    0.57
     않
    0.57
    ietic
    0.54
     Ino
    0.54
    않
    0.54
    DeleteBehavior
    0.53
    IMENTAL
    0.52
    Activations Density 3.130%

    No Known Activations