© 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. 7865
    Prev
    Next
    INDEX
    Explanations

    first and second person pronouns, as well as third person plural pronouns plus associated verbs

    oai_token-act-pair · gemini-2.0-flash

    personal pronouns

    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
     working
    -1.11
     holding
    -1.09
     marking
    -1.07
     calling
    -1.05
     sharing
    -1.05
     playing
    -1.05
     leaving
    -1.04
     joining
    -1.02
     fighting
    -1.02
     reading
    -1.02
    POSITIVE LOGITS
    Personendaten
    0.50
    kuuta
    0.46
    eseorang
    0.44
    óta
    0.43
     autorytatywna
    0.41
    зулта
    0.40
    Damit
    0.37
    matchCondition
    0.37
    esModule
    0.37
     Damit
    0.36
    Activations Density 5.632%

    No Known Activations