© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3518
    Prev
    Next
    INDEX
    Explanations

    the word "placed" or similar words related to location

    oai_token-act-pair · gemini-2.0-flash

    placed

    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
     giuri
    -0.98
     Jurí
    -0.94
     scolas
    -0.86
     umane
    -0.85
     Constitucional
    -0.85
     duquel
    -0.84
    Personensuche
    -0.83
    guien
    -0.82
     russa
    -0.82
     spirituale
    -0.82
    POSITIVE LOGITS
     Con
    0.69
    keted
    0.67
     Cons
    0.66
    QUES
    0.63
     “
    0.63
     Fan
    0.62
     fan
    0.62
    gradable
    0.61
    ^^^^^^^^
    0.61
    ctober
    0.60
    Activations Density 2.139%

    No Known Activations