© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9400
    Prev
    Next
    INDEX
    Explanations

    terms related to underwater exploration and technology

    oai_token-act-pair · gemini-2.0-flash

    underwater/marine environments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    __(/*!
    -0.73
    RuleContext
    -0.67
     continuant
    -0.63
    GEBURTS
    -0.59
     Preferencias
    -0.57
    fjspx
    -0.57
    GeoNames
    -0.56
    кисло
    -0.54
    djangoproject
    -0.52
    ApiProperty
    -0.52
    POSITIVE LOGITS
     underground
    0.71
     underwater
    0.69
     povezave
    0.66
    Underground
    0.65
    \{\\
    0.65
    underwater
    0.64
     Underground
    0.61
     subterranean
    0.60
    underground
    0.59
     Underwater
    0.53
    Activations Density 0.540%

    No Known Activations