© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4987
    Prev
    Next
    INDEX
    Explanations

    conditional phrases involving "want to" and "if you"

    oai_token-act-pair · gemini-2.0-flash

    want

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    PhysRevD
    -0.71
    Portail
    -0.71
    UVWXYZ
    -0.66
    PhysRevLett
    -0.65
    PhysRev
    -0.65
    hoeddwyd
    -0.65
     архивлан
    -0.63
    arschijnlijk
    -0.62
    rungsseite
    -0.62
     tetapi
    -0.60
    POSITIVE LOGITS
    hurst
    0.44
    RefNanny
    0.44
     yourself
    0.44
    orns
    0.43
    StartTag
    0.42
     granular
    0.41
    őz
    0.39
    KeySpec
    0.39
     lưu
    0.38
    pan
    0.38
    Activations Density 6.660%

    No Known Activations