© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 536
    Prev
    Next
    INDEX
    Explanations

    a proper noun followed by the word "as" and an adjective ending in "ed", or other very specific phrases used in scientific publications

    oai_token-act-pair · gemini-2.0-flash

    free

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    EndContext
    -0.68
     autorytatywna
    -0.68
    Diwedd
    -0.64
     CreateTagHelper
    -0.64
    tonsoft
    -0.60
    IUrlHelper
    -0.59
     createSlice
    -0.59
     للاسماء
    -0.58
    født
    -0.56
    ResumeLayout
    -0.56
    POSITIVE LOGITS
     free
    2.89
     Free
    2.52
    free
    2.50
    Free
    2.45
     FREE
    2.05
    FREE
    2.02
     libre
    1.58
     свобод
    1.51
     libres
    1.49
    自由
    1.44
    Activations Density 3.768%

    No Known Activations