Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10111
    Prev
    Next
    INDEX
    Explanations

    phrases in the context of business that include 'giving', services, values that are also conceptual, and information

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     gegeven
    -0.58
     offered
    -0.57
     presented
    -0.57
     distributed
    -0.52
     distribute
    -0.50
     given
    -0.50
     bestowed
    -0.49
     awarded
    -0.49
     Distributed
    -0.49
    zeczy
    -0.48
    POSITIVE LOGITS
     kepada
    0.94
     unto
    0.86
    แก่
    0.80
     aux
    0.69
     στους
    0.65
     agli
    0.63
     Unto
    0.59
    DIPSETTING
    0.58
     aos
    0.58
    omitempty
    0.57
    Activations Density 2.268%

    No Known Activations