© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6810
    Prev
    Next
    INDEX
    Explanations

    words related to places, activities and objects

    oai_token-act-pair · gemini-2.0-flash

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     tratto
    -0.55
     sjø
    -0.51
     that
    -0.50
    Однако
    -0.49
    但也
    -0.49
     themselves
    -0.49
     effectu
    -0.48
    ).]
    -0.48
    EREF
    -0.48
    épaisseur
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    1.05
    évaluateur
    0.91
    ⓧ
    0.80
    EndGlobalSection
    0.77
    EndInit
    0.77
     Numerade
    0.76
     متعلقه
    0.74
    addCriterion
    0.72
     виправивши
    0.71
    RTEE
    0.71
    Activations Density 1.603%

    No Known Activations