© 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. 1183
    Prev
    Next
    INDEX
    Explanations

    discussions about scientific topics or speculative fiction, frequently regarding near-future or future settings.

    oai_token-act-pair · gemini-2.0-flash

    space

    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
     intptr
    -0.65
    ="@+
    -0.57
    IsContent
    -0.56
    CreateModel
    -0.52
    はじめに
    -0.48
     glú
    -0.47
    Nazionale
    -0.47
    yped
    -0.47
     getM
    -0.47
     للمعارف
    -0.46
    POSITIVE LOGITS
     space
    3.00
    space
    2.64
     Space
    2.33
    Space
    2.33
     SPACE
    2.20
    SPACE
    1.99
     spaces
    1.89
     espaço
    1.79
    空间
    1.77
     espacio
    1.76
    Activations Density 7.530%

    No Known Activations