© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2710
    Prev
    Next
    INDEX
    Explanations

    the word "separate" and related forms.

    oai_token-act-pair · gemini-2.0-flash

    separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    DataAnnotations
    -0.81
    estima
    -0.58
     CHtml
    -0.54
     quelcon
    -0.52
     réguli
    -0.51
    éclairage
    -0.51
    HomeAsUpEnabled
    -0.50
    Selamat
    -0.50
    PostMapping
    -0.50
     bescha
    -0.49
    POSITIVE LOGITS
    分離
    0.79
     separation
    0.79
     isolated
    0.76
     isolation
    0.75
     separates
    0.75
     Isolated
    0.75
     isolate
    0.74
     Separate
    0.73
    Separate
    0.73
    separ
    0.71
    Activations Density 1.185%

    No Known Activations