© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    mentions of both political entities or people, and of numeric values or totals

    oai_token-act-pair · gemini-2.0-flash

    Political/financial entities receiving funds

    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
    تقاوى
    -0.72
    Personendaten
    -0.59
     defaultstate
    -0.57
    HasKey
    -0.54
    Geplaatst
    -0.48
    PostExecute
    -0.48
    raszamy
    -0.47
    oldown
    -0.47
    mphony
    -0.47
    endphp
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    0.59
    RegressionTest
    0.56
    mola
    0.53
    Portail
    0.50
    CppMethod
    0.49
    stdbool
    0.49
    }}/>
    0.48
    ("")]
    
    0.47
     Attachment
    0.47
    능
    0.47
    Activations Density 1.248%

    No Known Activations