© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    words that are parts of technical terms, whether medical, financial, legal, or technological

    oai_token-act-pair · gemini-2.0-flash

    legitim

    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
    ی
    -1.33
    er
    -1.17
    y
    -1.13
    e
    -1.05
    en
    -1.05
    ه
    -1.05
    es
    -0.99
    s
    -0.98
    a
    -0.96
    eer
    -0.92
    POSITIVE LOGITS
    èdia
    0.43
    ditionally
    0.40
    ofield
    0.38
     using
    0.38
     xong
    0.37
     utilisant
    0.36
    ometry
    0.36
    لكتر
    0.36
     USING
    0.36
    iente
    0.36
    Activations Density 2.377%

    No Known Activations