© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 14589
    Prev
    Next
    INDEX
    Explanations

    words related to edges, joints and connections either in the context of graphs/mathematics or more literal natural phenomenon or ball-related construction.

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
     leaves
    -1.38
     Leaves
    -1.16
     ends
    -1.11
    leaves
    -1.07
    Leaves
    -1.06
     Helps
    -1.00
     Keeps
    -0.99
    Helps
    -0.98
     keeps
    -0.98
     helps
    -0.96
    POSITIVE LOGITS
     ControllerBase
    0.52
    audiovisuel
    0.50
    ennom
    0.49
     spéciaux
    0.48
    XmlAccessType
    0.48
     lives
    0.48
     ObjectParameter
    0.48
    StackNavigator
    0.46
     intptr
    0.46
    illerato
    0.45
    Activations Density 8.842%

    No Known Activations