© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12952
    Prev
    Next
    INDEX
    Explanations

    scientific nomenclature for species, especially of plants and insects

    oai_token-act-pair · gemini-2.0-flash

    biological names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Rüyada
    -0.57
    woordig
    -0.46
     للاسماء
    -0.45
    +#+#
    -0.45
    dig
    -0.44
    Superview
    -0.42
     Mad
    -0.42
    cytic
    -0.41
    funciones
    -0.41
     fonctions
    -0.40
    POSITIVE LOGITS
    saraba
    0.57
    ScopeManager
    0.52
    رشف
    0.48
    HostException
    0.48
    featureID
    0.48
    RUnlock
    0.48
    MLLoader
    0.46
    AccessorTable
    0.45
    phazard
    0.45
    ConstraintMaker
    0.44
    Activations Density 0.516%

    No Known Activations