© 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. 9194
    Prev
    Next
    INDEX
    Explanations

    mentions of spoken languages, like English and Spanish

    oai_token-act-pair · gemini-2.0-flash

    programming languages

    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
     language
    -2.44
     Language
    -2.34
    Language
    -2.27
    language
    -2.20
     LANGUAGE
    -2.16
     languages
    -2.11
     Languages
    -1.96
    LANGUAGE
    -1.92
    语言
    -1.84
    Languages
    -1.80
    POSITIVE LOGITS
     awakeFromNib
    0.53
    OfWork
    0.48
    Timmy
    0.46
    сылкі
    0.45
    /*!
    0.44
     Gillespie
    0.43
    PickerController
    0.43
    WireFormatLite
    0.43
    greens
    0.43
     Patreon
    0.42
    Activations Density 1.381%

    No Known Activations