© 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. 14709
    Prev
    Next
    INDEX
    Explanations

    personal pronouns used in the context of events

    oai_token-act-pair · gemini-2.0-flash

    General short texts

    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
    Put
    -0.78
     put
    -0.76
     read
    -0.75
     Read
    -0.73
    Cut
    -0.72
    Read
    -0.71
     cut
    -0.71
     Put
    -0.69
     Cut
    -0.68
     let
    -0.67
    POSITIVE LOGITS
    TagHelpers
    0.63
    Autoritní
    0.57
    WebVitals
    0.57
    prefixer
    0.53
     adjourn
    0.53
     chant
    0.52
     rake
    0.52
     garnish
    0.51
     Jefus
    0.50
    Lähteet
    0.49
    Activations Density 3.447%

    No Known Activations