© 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. 6512
    Prev
    Next
    INDEX
    Explanations

    text related to communication and social sciences, particularly the transfer of information between speakers.

    oai_token-act-pair · gemini-2.0-flash

    Language and information processing

    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
    MessageTagHelper
    -0.75
    ItemBackground
    -0.70
     Waray
    -0.66
    UpInside
    -0.61
     betweenstory
    -0.59
     BorderRadius
    -0.59
    selaer
    -0.59
    Архівовано
    -0.59
    MLLoader
    -0.58
    Personendaten
    -0.57
    POSITIVE LOGITS
     unknownFields
    0.55
    gameserver
    0.46
     eqn
    0.44
     faltar
    0.44
     igualdad
    0.43
     niches
    0.43
    laughs
    0.42
     découver
    0.42
     exhibitors
    0.42
     maíz
    0.41
    Activations Density 8.066%

    No Known Activations