© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6875
    Prev
    Next
    INDEX
    Explanations

    text about ex-partners contacting each other after a break

    oai_token-act-pair · gemini-2.0-flash

    Conversational/code snippets

    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
     beginnetje
    -0.61
     commercio
    -0.54
    íncia
    -0.53
    /******/
    -0.52
     umum
    -0.52
    tování
    -0.49
     betweenstory
    -0.48
    phous
    -0.48
    ValueGenerated
    -0.48
     åter
    -0.48
    POSITIVE LOGITS
     onAnimation
    0.57
    ArgsConstructor
    0.54
    hasMoreElements
    0.51
    ğraf
    0.50
    Viitteet
    0.50
    发表于
    0.47
     ALG
    0.46
    ExtendWith
    0.46
    AxisAlignment
    0.46
     pylint
    0.45
    Activations Density 32.434%

    No Known Activations