© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2830
    Prev
    Next
    INDEX
    Explanations

    descriptive words in a sentence alongside the verb 'to be'

    oai_token-act-pair · gemini-2.0-flash

    Descriptions of items

    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
    AndEndTag
    -1.19
    findpost
    -1.03
     كومونز
    -1.02
     Италијани
    -0.98
    tagHelperRunner
    -0.95
     يتيمه
    -0.91
     InputDecoration
    -0.90
    LookAnd
    -0.86
    rrggbb
    -0.85
    AnimationsModule
    -0.84
    POSITIVE LOGITS
    DC
    0.49
    IsNotEmpty
    0.46
     cas
    0.44
    위
    0.43
     v
    0.42
     hall
    0.40
     screen
    0.39
     c
    0.39
    Symbol
    0.39
     Ergänzung
    0.38
    Activations Density 1.280%

    No Known Activations