© 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. 8042
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and auxiliary verbs, and phrases "something went wrong" and "gone out"

    oai_token-act-pair · gemini-2.0-flash

    Something went wrong

    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
     go
    -2.20
    go
    -1.84
    Go
    -1.70
     Go
    -1.69
     goes
    -1.40
     GO
    -1.33
    GO
    -1.27
    goes
    -1.13
     Goes
    -1.01
    Goes
    -0.88
    POSITIVE LOGITS
    WithIOException
    0.88
     ostavi
    0.75
    enterOuterAlt
    0.69
    :+:
    0.66
    tvguidetime
    0.64
     initComponents
    0.57
    ніципалі
    0.56
     kasarigan
    0.56
    niająca
    0.54
    دانشنامهٔ
    0.54
    Activations Density 3.645%

    No Known Activations