© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3875
    Prev
    Next
    INDEX
    Explanations

    mentions of "world" followed by certain characters such as a hyphen, verbs, or adjectives.

    oai_token-act-pair · gemini-2.0-flash

    world famous

    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
    Rüyada
    -0.59
     ngờ
    -0.52
    itarianism
    -0.50
    Z
    -0.46
    itarian
    -0.46
    قاب
    -0.45
    cèse
    -0.45
    criptive
    -0.45
     [*]
    -0.44
    ques
    -0.43
    POSITIVE LOGITS
    (!__
    0.70
    rungsseite
    0.62
    < 
    0.56
    AutoScaleMode
    0.56
    IntoConstraints
    0.54
    FormTagHelper
    0.54
    {}\
    0.52
    ագրություններ
    0.52
    //
    0.52
    DebuggerNonUser
    0.51
    Activations Density 7.031%

    No Known Activations