© 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. 7830
    Prev
    Next
    INDEX
    Explanations

    words that are possessive or related to the concept of ownership or requirements

    oai_token-act-pair · gemini-2.0-flash

    new

    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
     conditions
    -0.93
    conditions
    -0.92
     constraints
    -0.92
     requirements
    -0.91
     emotions
    -0.90
    constraints
    -0.90
    CONDITIONS
    -0.89
     effects
    -0.88
     restrictions
    -0.86
    requirements
    -0.86
    POSITIVE LOGITS
     ujednoznacz
    0.62
     iprot
    0.59
    󠁿
    0.57
    pexpr
    0.54
    writeFieldEnd
    0.53
     AspNetCore
    0.53
     CURIAM
    0.50
     мѣ
    0.49
    endphp
    0.48
    ineno
    0.48
    Activations Density 10.216%

    No Known Activations